© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5922
    Prev
    Next
    INDEX
    Explanations

    visual separators or dividers in text, like vertical bars or lines

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

    large numerical or computational values, like dates, page numbers, or long numeric sequences.

    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
    BrowserRouter
    -0.47
     références
    -0.46
     Henson
    -0.45
    TemporalType
    -0.44
     getText
    -0.43
     answer
    -0.43
    HomeAsUpEnabled
    -0.43
    ‟
    -0.43
     BrowserRouter
    -0.43
     fon
    -0.42
    POSITIVE LOGITS
    |
    1.13
     |
    1.13
    +|
    1.03
     $|
    1.00
    {|
    0.98
    $|
    0.93
    ("|
    0.93
    '|
    0.92
    |\
    0.91
    >|</
    0.91
    Activations Density 0.067%

    No Known Activations