© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1353
    Prev
    Next
    INDEX
    Explanations

    references to a public's response to governance or political actions

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

    People or groups acting collectively

    np_acts-logits-general · gemini-2.0-flash

    people voting or expressing opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NB
    -0.48
    chelles
    -0.47
    Bronnen
    -0.46
    çek
    -0.45
    Help
    -0.45
    SuspendLayout
    -0.45
    ใช่
    -0.44
    ///</
    -0.44
    ignée
    -0.44
    ULUM
    -0.42
    POSITIVE LOGITS
     collectively
    0.82
     saites
    0.75
    IsContent
    0.66
    Datuak
    0.66
     yourselves
    0.65
     kollek
    0.64
     overwhelmingly
    0.64
     Lech
    0.63
     moviliz
    0.63
     للمعارف
    0.63
    Activations Density 0.325%

    No Known Activations