© 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. 20-GEMMASCOPE-RES-16K
    11. 3360
    Prev
    Next
    INDEX
    Explanations

    HTML elements and their attributes

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

    HTML list items and tags

    np_acts-logits-general · gemini-2.0-flash

    list items and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     onCancelled
    -0.62
     незавершена
    -0.61
    ніципа
    -0.60
    Бахар
    -0.57
    Geplaatst
    -0.55
    endpush
    -0.54
    providedIn
    -0.52
     "<?
    -0.52
     GeoNames
    -0.51
    htdocs
    -0.51
    POSITIVE LOGITS
     للاسماء
    0.79
    QMetaType
    0.71
    FieldDescriptor
    0.63
    elemField
    0.62
    findpost
    0.60
     Administrativna
    0.58
    StoreMessageInfo
    0.57
    fjspx
    0.57
     >=",
    0.56
    MigrationBuilder
    0.55
    Activations Density 0.155%

    No Known Activations