© 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. 4665
    Prev
    Next
    INDEX
    Explanations

    indications related to specific medical treatments and their usage

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

    financial and legal terminology, particularly related to business documents, services, and disclaimers.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
     surla
    -0.59
    varlak
    -0.52
    addContainerGap
    -0.48
    Researcher
    -0.48
     تضيفلها
    -0.48
    tizens
    -0.48
    MLLoader
    -0.47
    ніципалі
    -0.47
    arschijnlijk
    -0.45
    Kariera
    -0.44
    POSITIVE LOGITS
     мәкал
    0.46
    PerformLayout
    0.38
    ɵɵ
    0.33
     beginnetje
    0.32
    Sim
    0.32
    RegressionTest
    0.31
    #/
    0.31
     Ślą
    0.30
    ፩
    0.29
    sinon
    0.29
    Activations Density 0.210%

    No Known Activations