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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5152
    Prev
    Next
    INDEX
    Explanations

    phrases indicating locations and recommendations

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

    start of documents or beginning of a text section (indicated by <bos> tokens with high activation).

    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
     partij
    -0.35
     صوتيه
    -0.35
     tegas
    -0.34
     numberOfRows
    -0.33
    keyColumn
    -0.32
    rzost
    -0.31
    visející
    -0.31
    Diwedd
    -0.31
    rån
    -0.30
     समीक्षाओं
    -0.30
    POSITIVE LOGITS
     Chrift
    0.48
    localctx
    0.47
    ScopeManager
    0.46
    addContainerGap
    0.46
     Efq
    0.46
    posits
    0.46
     great
    0.45
    ſſer
    0.44
    parking
    0.44
    真心
    0.44
    Activations Density 0.011%

    No Known Activations