© 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. 31-GEMMASCOPE-RES-131K
    6. 24623
    Prev
    Next
    INDEX
    Explanations

    references to specific programming-related terms and chemical compounds

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

    HttpClient, HCl, bicarbonate, blackjack

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.59
    MessageOf
    -0.57
    Välislingid
    -0.52
     arit
    -0.47
     MutableLiveData
    -0.46
    RetentionPolicy
    -0.45
     Maul
    -0.45
    әрмәләр
    -0.43
    GIVEREF
    -0.43
    quelize
    -0.43
    POSITIVE LOGITS
     HttpClient
    0.83
    HttpClient
    0.68
     httpClient
    0.54
     griego
    0.50
     barriga
    0.47
    uxxxx
    0.45
     embreagem
    0.45
     ciudadano
    0.45
     ciudadanía
    0.44
     grecque
    0.44
    Activations Density 0.022%

    No Known Activations