© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1060
    Prev
    Next
    INDEX
    Explanations

    references to awards and recognitions, particularly in a historical or ceremonial context

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

    proper names and notable achievements, particularly in sports, politics, and awards.

    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
     constantly
    -0.34
     springfox
    -0.32
    ɵɵ
    -0.29
     body
    -0.29
    DatabaseError
    -0.29
     demografica
    -0.29
     onBind
    -0.28
     ali
    -0.28
     ab
    -0.27
     Body
    -0.27
    POSITIVE LOGITS
    parsedMessage
    0.60
    LabelTagHelper
    0.57
     nakalista
    0.56
    agissait
    0.56
    ViewFeatures
    0.56
    ⓧ
    0.55
     betweenstory
    0.54
    
    0.54
    tamment
    0.52
     Geſch
    0.52
    Activations Density 0.291%

    No Known Activations