© 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. 8-GEMMASCOPE-RES-16K
    11. 11471
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "re"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ivelany
    -0.82
     Henson
    -0.73
     Lons
    -0.73
     الفلك
    -0.70
    Jody
    -0.69
     AssemblyCulture
    -0.68
    nyez
    -0.68
     Farley
    -0.67
     Jonas
    -0.66
    anyon
    -0.66
    POSITIVE LOGITS
     StatelessWidget
    0.86
     youre
    0.86
    WithFormat
    0.81
     precisione
    0.78
     syke
    0.77
    rahman
    0.76
    re
    0.76
    tire
    0.76
    Lähteet
    0.76
     fertiliser
    0.75
    Activations Density 0.086%

    No Known Activations