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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 8193
    Prev
    Next
    INDEX
    Explanations

    references to population health statistics and medical comparisons among different regions and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unction
    -0.52
     World
    -0.48
    elsch
    -0.46
    verhältnis
    -0.46
    multicolumn
    -0.45
     ext
    -0.44
    ActionPerformed
    -0.44
    tiez
    -0.43
     legyen
    -0.42
    NOR
    -0.41
    POSITIVE LOGITS
     propOrder
    1.12
    ValueStyle
    0.92
     myſelf
    0.89
    EndContext
    0.76
     Efq
    0.75
     كومونز
    0.72
     itſelf
    0.71
     nahilalakip
    0.71
     ſhe
    0.70
     himſelf
    0.70
    Activations Density 0.700%

    No Known Activations