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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 14096
    Prev
    Next
    INDEX
    Explanations

    references to general counsel or legal roles within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.90
    enumi
    -0.79
    IntoConstraints
    -0.77
     myſelf
    -0.76
    EndContext
    -0.76
     HasFactory
    -0.73
    󠁿
    -0.71
     aught
    -0.71
    tagHelperRunner
    -0.70
     poffible
    -0.66
    POSITIVE LOGITS
    purpose
    0.84
     purpose
    0.83
    issimo
    0.82
    GENERAL
    0.69
    General
    0.64
     General
    0.64
    ist
    0.63
    izable
    0.63
     GENERAL
    0.63
     general
    0.62
    Activations Density 0.093%

    No Known Activations