© 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. 9-GEMMASCOPE-RES-131K
    6. 6732
    Prev
    Next
    INDEX
    Explanations

    names and terms related to literature, specifically referencing prominent figures and concepts in math and programming

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

    names and programming terms

    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
     lendemain
    -0.38
     espoir
    -0.35
     desee
    -0.32
     Nuestro
    -0.32
     Republik
    -0.32
     bahía
    -0.32
     maintenir
    -0.31
     Constitucional
    -0.30
     Bundesrepublik
    -0.30
     productivo
    -0.30
    POSITIVE LOGITS
    MENAFN
    0.85
     يتيمه
    0.81
    esgue
    0.78
    databind
    0.76
     PackageManager
    0.70
    Carriera
    0.69
    parsedMessage
    0.68
    Suara
    0.68
    figer
    0.68
    funeral
    0.67
    Activations Density 0.023%

    No Known Activations