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. 9427
    Prev
    Next
    INDEX
    Explanations

    words related to evacuation or emergency-related scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    starting with "Ev", "Av", "lev" or "lov"

    np_acts-logits-general · gemini-2.0-flash

    ev, lev, lov, av, ov prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    GraphicsUnit
    -0.70
    extAlignment
    -0.66
    er
    -0.61
     للمعارف
    -0.60
     صوتيه
    -0.55
    erent
    -0.55
     HasFactory
    -0.54
    ifstream
    -0.54
     IBOutlet
    -0.52
    MOC
    -0.51
    POSITIVE LOGITS
    olutions
    0.66
    illage
    0.56
    vv
    0.55
    ouac
    0.54
    v
    0.53
    vy
    0.52
    itz
    0.51
    ्ह
    0.50
    WriteAttribute
    0.50
     Mev
    0.50
    Activations Density 0.256%

    No Known Activations