© 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. 3-GEMMASCOPE-RES-16K
    11. 5940
    Prev
    Next
    INDEX
    Explanations

    function definitions and declarations in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.87
     Efq
    -0.85
     Theſe
    -0.82
     ARXIV
    -0.76
     ſeveral
    -0.74
     Chriftian
    -0.71
     myſelf
    -0.71
     Jefus
    -0.71
    umably
    -0.70
     الحره
    -0.69
    POSITIVE LOGITS
     des
    0.55
    parsedMessage
    0.47
     her
    0.47
     положи
    0.43
    霆
    0.43
    iny
    0.43
    プーン
    0.42
     que
    0.42
    <eos>
    0.42
     effect
    0.42
    Activations Density 0.021%

    No Known Activations