© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1449
    Prev
    Next
    INDEX
    Explanations

    key terms and identifiers related to corporate and technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, file paths, or software names

    np_acts-logits-general · gemini-2.0-flash

    src/ paths and math

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jagung
    -0.38
     actualidad
    -0.36
     bénévoles
    -0.36
    ControllerAdvice
    -0.34
    хотво
    -0.34
     communs
    -0.33
     boat
    -0.32
    Ligações
    -0.32
     noqa
    -0.32
    UserScript
    -0.31
    POSITIVE LOGITS
    dflare
    0.63
     يتيمه
    0.57
     Numerade
    0.56
    RTHOOK
    0.50
    цездатний
    0.50
    RegistryLite
    0.47
    Xiv
    0.47
     PIA
    0.45
    nodoc
    0.44
    ProgressHUD
    0.44
    Activations Density 0.175%

    No Known Activations