© 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. 17-GEMMASCOPE-RES-16K
    11. 10620
    Prev
    Next
    INDEX
    Explanations

    specific statistical terms and variables related to data analysis and results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     â
    -0.95
    AndEndTag
    -0.82
    Â
    -0.71
     Â
    -0.70
     …
    -0.64
    â
    -0.64
    ViewImports
    -0.63
    ftagPool
    -0.63
    RuleContext
    -0.63
    UrlResolution
    -0.61
    POSITIVE LOGITS
    Personensuche
    0.77
    ...@
    0.71
    --
    0.67
    Життєпис
    0.64
    ükemmel
    0.64
    ...
    0.62
    שְׁ
    0.60
    Externé
    0.59
    "....
    0.58
    —
    0.58
    Activations Density 2.764%

    No Known Activations