© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5520
    Prev
    Next
    INDEX
    Explanations

    markers indicating the beginning of significant content sections in text

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

    Follows words related to processes or rules

    np_acts-logits-general · gemini-2.0-flash

    metabolic process or substance

    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
    komendasi
    -0.61
    ̍t
    -0.59
    formaz
    -0.54
    enderror
    -0.54
    исленность
    -0.54
    örer
    -0.50
     totalSupply
    -0.50
    }';
    -0.50
     gitara
    -0.50
    gages
    -0.48
    POSITIVE LOGITS
     CreateTagHelper
    0.89
     snippetHide
    0.77
     للاسماء
    0.70
     ExecuteAsync
    0.66
    RenderAtEndOf
    0.60
    LayoutConstraint
    0.59
     autorytatywna
    0.57
    providedIn
    0.55
     SwiftUI
    0.55
    TagMode
    0.55
    Activations Density 0.046%

    No Known Activations