Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 11291
    Prev
    Next
    INDEX
    Explanations

    terms related to variety and diversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ings
    -0.83
    ations
    -0.82
    }{*}{
    -0.78
    ️
    -0.77
    ly
    -0.73
     שוליים
    -0.69
    ם
    -0.68
    est
    -0.68
    ening
    -0.68
    aneous
    -0.67
    POSITIVE LOGITS
    yyy
    0.99
    yyyy
    0.98
    e
    0.84
    yyyyy
    0.79
    eis
    0.68
    YYY
    0.66
    ます
    0.65
    outube
    0.63
    ますね
    0.61
    yy
    0.61
    Activations Density 0.752%

    No Known Activations