© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 581
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements

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

    occurrences of code-related syntax or directives

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

    #define and #include directives

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ]))
    -0.77
    )");
    -0.74
    >');
    -0.73
    inheit
    -0.73
    "));
    -0.71
    "){
    -0.70
    )];
    -0.70
    "):
    -0.69
    ()]
    -0.69
    ")));
    -0.68
    POSITIVE LOGITS
    .#
    1.08
     #
    1.06
    \#
    0.95
     noqa
    0.94
    :#
    0.92
     (#
    0.90
    -#
    0.88
     \#
    0.87
    \#\#
    0.87
    /#
    0.82
    Activations Density 0.165%

    No Known Activations