© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 9279
    Prev
    Next
    INDEX
    Explanations

    references to health-related surveys or checks

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

    local councils or boroughs

    np_acts-logits-general · gemini-2.0-flash

    local council or authority

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.95
    RenderAtEndOf
    -0.85
    AsUp
    -0.80
    contentLoaded
    -0.72
    IndentedString
    -0.72
    ьаж
    -0.71
     Catawiki
    -0.71
     resourceCulture
    -0.70
    TextAppearance
    -0.69
    ViewFeatures
    -0.68
    POSITIVE LOGITS
     council
    1.47
     Council
    1.27
    Council
    1.19
    council
    1.17
     COUNCIL
    1.14
     councillors
    1.10
     Cllr
    1.08
     councils
    1.06
    Cllr
    1.05
     councillor
    1.03
    Activations Density 0.114%

    No Known Activations