© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 66342
    Prev
    Next
    INDEX
    Explanations

    references to food establishments and culinary terms

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

    places and establishments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.59
    afficheront
    -0.59
    脚注の使い方
    -0.58
     yyr
    -0.55
    endphp
    -0.55
    ConverterFactory
    -0.54
    oredCriteria
    -0.53
    utilisons
    -0.52
    FunctionFlags
    -0.52
    WebVitals
    -0.52
    POSITIVE LOGITS
     inspire
    0.35
    simplify
    0.35
     Bünd
    0.34
     soulful
    0.34
     simplify
    0.34
    ulemon
    0.34
     evolucion
    0.33
     adaptive
    0.33
     crave
    0.33
    kozá
    0.32
    Activations Density 0.141%

    No Known Activations