© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4845
    Prev
    Next
    INDEX
    Explanations

    API-related function calls and operations

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

    code-related tokens and programming syntax, particularly from API and programming contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    code patterns for API endpoints and CRUD-style method calls (get/fetch/list/create/update/delete), often involving IDs, lists, and request execution in programming snippets.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    method or function definitions in code, particularly in object-oriented programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    dafx
    -0.56
    ьаж
    -0.52
     cherchés
    -0.51
     Administrativna
    -0.51
    ValueStyle
    -0.47
    saraba
    -0.47
    matchCondition
    -0.46
    Chham
    -0.45
    UserScript
    -0.45
     Exacts
    -0.44
    POSITIVE LOGITS
     насељу
    0.52
    DeleteMapping
    0.44
     MediatR
    0.43
    bootstrapcdn
    0.40
    idget
    0.38
     gna
    0.37
     ModelExpression
    0.36
    audiovisuel
    0.36
    CRD
    0.36
    inburgh
    0.35
    Activations Density 0.147%

    No Known Activations