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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 55382
    Prev
    Next
    INDEX
    Explanations

    JavaScript function call terminators or endings (specifically semicolons in require statements)

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

    closing parentheses and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ſcher
    -0.95
    findpost
    -0.94
    <unused16>
    -0.90
    <unused14>
    -0.90
    <unused28>
    -0.90
    <unused23>
    -0.90
    <unused51>
    -0.90
    <unused52>
    -0.90
    [@BOS@]
    -0.90
    <unused3>
    -0.90
    POSITIVE LOGITS
    ');
    0.59
    ).
    0.55
    ());
    0.55
    ])
    0.54
    '))
    0.52
    ));
    0.52
    });
    0.52
    ').
    0.52
    ')
    0.51
     ).
    0.51
    Activations Density 0.001%

    No Known Activations