© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8955
    Prev
    Next
    INDEX
    Explanations

    terms related to clinical data analysis and genetic testing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical details about medical research and data processing, especially in the context of genetic or clinical studies.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    formal, institutional descriptions of clinical or research operations, including administrative context, workflows, facilities, and timelines.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    names of institutions or departments

    oai_token-act-pair · deepseek-r1Triggered by @jyhe0408

    institutional or organizational names and locations in academic/medical research contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stuff
    -0.40
    
    -0.35
    tanleria
    -0.34
    PhysRev
    -0.34
    ⤹
    -0.33
     anything
    -0.30
     sm
    -0.30
     henne
    -0.29
     you
    -0.29
     everything
    -0.29
    POSITIVE LOGITS
     betweenstory
    0.73
    WriteBarrier
    0.64
    StoryboardSegue
    0.63
    PerformLayout
    0.62
    IsMutable
    0.60
    colgante
    0.60
    HomeAsUpEnabled
    0.57
    出版年
    0.57
    AutoField
    0.56
    llavero
    0.55
    Activations Density 1.057%

    No Known Activations