© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 1881
    Prev
    Next
    INDEX
    Explanations

    references to figures and plotting in a document

    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
    UnitTesting
    -0.85
     Monfieur
    -0.85
    awtextra
    -0.83
     Efq
    -0.83
     becauſe
    -0.82
     itſelf
    -0.81
    BeginContext
    -0.80
    principalColumn
    -0.80
     againſt
    -0.80
     nahilalakip
    -0.79
    POSITIVE LOGITS
    fig
    1.70
     fig
    1.34
     plt
    0.89
    figs
    0.89
    FIG
    0.88
     olive
    0.81
     FIG
    0.79
    *{
    0.78
     figs
    0.77
    olive
    0.73
    Activations Density 0.151%

    No Known Activations