© 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. 10-GEMMASCOPE-RES-16K
    11. 4353
    Prev
    Next
    INDEX
    Explanations

    underscore characters in variable and function names or parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Accessors
    -0.48
     Geschäfte
    -0.48
     Geschäft
    -0.47
     Савез
    -0.46
     yana
    -0.46
     égal
    -0.46
     måned
    -0.45
    InMillis
    -0.45
    WebControls
    -0.44
     applicazioni
    -0.44
    POSITIVE LOGITS
     فريبيس
    0.91
    GEBURTS
    0.76
     للمعارف
    0.76
    APORE
    0.75
     виправивши
    0.74
     كومونز
    0.73
    Autoritní
    0.72
    PYX
    0.71
     مرئيه
    0.71
    abestanden
    0.70
    Activations Density 0.529%

    No Known Activations