Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4614
    Prev
    Next
    INDEX
    Explanations

    punctuation and closing brackets

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

    Code snippets containing special characters

    np_acts-logits-general · gemini-2.0-flash

    code structure endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    Externí
    -0.51
    -
    -0.45
    EditorBrowsable
    -0.43
     vostri
    -0.42
    جستارهای
    -0.42
     setw
    -0.42
    ;
    -0.41
     sahaja
    -0.41
    lem
    -0.41
     {};
    
    -0.40
    POSITIVE LOGITS
    ↵
    0.91
     //
    0.82
    ViewFeatures
    0.82
     —,
    0.80
    ?',
    0.80
    ________,
    0.79
    ?",
    0.78
    %",
    0.78
     }),
    0.77
     \%,
    0.77
    Activations Density 0.178%

    No Known Activations