© 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. 1463
    Prev
    Next
    INDEX
    Explanations

    mentions of patterns, issues, and relevant findings in a discussion or explanation context

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

    problems or features

    np_acts-logits-general · gemini-2.0-flash

    discussing specific aspects or features

    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
    spesies
    -0.46
    PathVariable
    -0.42
    ̈́
    -0.42
     stuks
    -0.42
    ⟬
    -0.41
    chemise
    -0.41
    +#+
    -0.39
    NameInMap
    -0.39
    jooq
    -0.39
     يتيمه
    -0.38
    POSITIVE LOGITS
     features
    0.64
    IntoConstraints
    0.62
    Особенности
    0.57
     things
    0.56
     Features
    0.55
    features
    0.53
    бливості
    0.52
     nuances
    0.51
    Cechy
    0.51
    DispatchToProps
    0.51
    Activations Density 0.907%

    No Known Activations