© 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. 38399
    Prev
    Next
    INDEX
    Explanations

    syntax related to programming constructs, particularly object-oriented programming and data structures

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

    lists of values

    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
    Климат
    -0.40
     userData
    -0.35
     utilizan
    -0.35
    CustomerID
    -0.35
    understand
    -0.35
     bénévoles
    -0.35
    Woo
    -0.34
    RNA
    -0.34
     utford
    -0.34
    子的
    -0.34
    POSITIVE LOGITS
     collection
    0.99
     list
    0.98
    collection
    0.81
     coleção
    0.77
     COLLECTION
    0.75
     kumpulan
    0.75
     listado
    0.74
     lijst
    0.74
     Sammlung
    0.73
     lista
    0.73
    Activations Density 0.100%

    No Known Activations