© 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. 17-GEMMASCOPE-RES-16K
    6. 7408
    Prev
    Next
    INDEX
    Explanations

    negation phrases in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.68
    núť
    -0.56
    ASTIC
    -0.56
    lık
    -0.54
    infall
    -0.54
    tacles
    -0.53
    itaire
    -0.51
     nice
    -0.50
    ضات
    -0.50
     Enlightenment
    -0.49
    POSITIVE LOGITS
    Nor
    1.12
     nor
    1.07
     Nor
    1.04
     NOR
    1.02
    nor
    1.01
    NOR
    0.90
     tampoco
    0.87
    therners
    0.85
     siquiera
    0.85
     Nore
    0.77
    Activations Density 0.088%

    No Known Activations