© 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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3976
    Prev
    Next
    INDEX
    Explanations

    function calls and method chaining in programming code

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

    Code related to testing; expecting a certain value

    np_acts-logits-general · gemini-2.0-flash

    closing parenthesis assertion

    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
     ver
    -0.55
    (
    -0.52
     est
    -0.50
     mo
    -0.50
     sost
    -0.50
    ar
    -0.50
     los
    -0.48
    ,
    -0.48
     na
    -0.47
     pris
    -0.47
    POSITIVE LOGITS
    ")));
    
    0.92
     myſelf
    0.91
     متعلقه
    0.90
    )";
    
    0.90
    )");
    
    0.88
    RenderAtEndOf
    0.88
    AnchorStyles
    0.88
    .";
    
    0.85
    $")
    0.85
    醐
    0.83
    Activations Density 0.040%

    No Known Activations