© 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. 12625
    Prev
    Next
    INDEX
    Explanations

    function calls related to instance retrieval or initialization in 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
     <<<<<<<<<<<<<<
    -0.74
    cemic
    -0.62
    \}\\
    -0.60
    jsp
    -0.60
     хозяй
    -0.56
    ませんが
    -0.56
    __)
    -0.55
    stimulated
    -0.55
     Kitz
    -0.55
    moso
    -0.55
    POSITIVE LOGITS
    getInstance
    1.25
     Jeff
    0.97
    Jeff
    0.95
     getInstance
    0.89
     JEFF
    0.81
     jeff
    0.80
    AnimationsModule
    0.73
    ;#
    0.72
     MessageBoxIcon
    0.65
    JEFF
    0.65
    Activations Density 0.011%

    No Known Activations