© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1133
    Prev
    Next
    INDEX
    Explanations

    names, titles, and designations related to music and awards

    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
    ged
    -0.83
    ted
    -0.79
    rossed
    -0.75
    ounted
    -0.72
    GED
    -0.71
    iked
    -0.70
    reciated
    -0.69
    ourced
    -0.68
    TED
    -0.67
    aked
    -0.66
    POSITIVE LOGITS
     Roskov
    0.82
    fony
    0.82
    Dmit
    0.79
     esternos
    0.79
     Chwiliwch
    0.79
    Portail
    0.79
    newBuilder
    0.77
    Pautan
    0.77
    enumi
    0.76
     Dmit
    0.76
    Activations Density 4.870%

    No Known Activations