© 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. 11-GEMMASCOPE-RES-16K
    11. 13364
    Prev
    Next
    INDEX
    Explanations

    special formatting and comments in code or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    @[+][
    -0.66
    AppCompatTheme
    -0.55
    έα
    -0.53
    NewRow
    -0.53
    createCanvas
    -0.51
    styleable
    -0.51
    icali
    -0.47
     Curitiba
    -0.47
     Ayala
    -0.47
    downloaded
    -0.47
    POSITIVE LOGITS
     noqa
    4.46
     defaultstate
    0.93
    migrations
    0.90
     nahilalakip
    0.89
    WireFormatLite
    0.86
    providedIn
    0.84
    Становништво
    0.81
    RegistryLite
    0.80
    scriptcase
    0.78
    jupiter
    0.77
    Activations Density 0.029%

    No Known Activations