© 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. 4-GEMMASCOPE-RES-16K
    11. 970
    Prev
    Next
    INDEX
    Explanations

    references to actions involving "cutting" or "reducing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.95
    BibitemShut
    -0.89
    bibfield
    -0.86
     Senhora
    -0.82
    PANY
    -0.81
    bibinfo
    -0.80
    Puis
    -0.79
    ValueStyle
    -0.78
    ,:);
    -0.77
    Amicalement
    -0.77
    POSITIVE LOGITS
     cut
    2.77
     Cut
    2.63
    cut
    2.59
     cuts
    2.50
    Cut
    2.49
     CUT
    2.48
    CUT
    2.29
     Cuts
    2.25
     cutting
    2.25
    cuts
    2.18
    Activations Density 0.031%

    No Known Activations