© 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. 82792
    Prev
    Next
    INDEX
    Explanations

    specific named entities or categories related to geographical locations and organizations

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

    County, electrodes, zinc, trials

    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
     CreateTagHelper
    -0.75
    LookAnd
    -0.61
    contentLoaded
    -0.56
    AddTagHelper
    -0.53
    anical
    -0.51
    orsese
    -0.51
    دانشنامهٔ
    -0.50
     Wikimedijinoj
    -0.49
    findpost
    -0.49
    EndContext
    -0.48
    POSITIVE LOGITS
     getById
    0.36
     EconPapers
    0.34
    ています
    0.30
    haikusbot
    0.30
    webElementXpaths
    0.29
     Catawiki
    0.28
     kabát
    0.28
     goederen
    0.28
     getCustomer
    0.27
     resourceCulture
    0.27
    Activations Density 0.007%

    No Known Activations