© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 80844
    Prev
    Next
    INDEX
    Explanations

    function calls related to retrieving values or data

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

    getter methods

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     deleteById
    -0.84
     queſta
    -0.78
     newNode
    -0.76
     companyId
    -0.75
     onClose
    -0.74
    SBATCH
    -0.73
     accountId
    -0.73
     columnIndex
    -0.72
     للاسماء
    -0.72
     itemId
    -0.71
    POSITIVE LOGITS
    get
    1.35
    Get
    1.05
     get
    0.96
     Get
    0.93
    GET
    0.87
     GET
    0.72
     gets
    0.66
    Gets
    0.66
     obtiene
    0.63
     Obtener
    0.63
    Activations Density 0.020%

    No Known Activations