© 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. 15340
    Prev
    Next
    INDEX
    Explanations

    variables related to the properties or status of items in a structured data format

    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
     myſelf
    -1.16
     itſelf
    -1.15
    RenderAtEndOf
    -1.14
     Monfieur
    -1.07
     Jefus
    -1.07
     Efq
    -1.03
     ་་
    -0.97
    ViewFeatures
    -0.97
    yntaxException
    -0.96
     Wikimedijinoj
    -0.95
    POSITIVE LOGITS
    setUse
    0.70
    ↵↵
    0.60
     dis
    0.59
     or
    0.56
    -
    0.55
    setDo
    0.54
     N
    0.53
    in
    0.52
    no
    0.52
    _
    0.52
    Activations Density 0.263%

    No Known Activations