© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5587
    Prev
    Next
    INDEX
    Explanations

    function and method signatures in code

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

    Code snippets ending in closing curly brackets/parenthesis

    np_acts-logits-general · gemini-2.0-flash

    code parsing and structuring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stdc
    -0.62
    ():
    -0.55
    '||
    -0.54
    ioutil
    -0.54
    <>
    -0.54
    `;
    -0.52
    sidemargin
    -0.51
    '];
    -0.51
    -0.51
    HomeAsUpEnabled
    -0.51
    POSITIVE LOGITS
     {
    0.67
    تقاوى
    0.61
    ViewFeatures
    0.61
    AutoScaleMode
    0.60
     FishBase
    0.57
     throws
    0.56
    hyrchwyd
    0.56
    enderror
    0.52
     الاطلاع
    0.50
     Polícia
    0.50
    Activations Density 0.063%
    No Known Activations