© 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. 24487
    Prev
    Next
    INDEX
    Explanations

    patterns related to coding commands and utilities in programming contexts

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

    special operations

    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
    <?
    -0.52
    はじめに
    -0.47
    GEBURTSDATUM
    -0.44
    ChildScrollView
    -0.44
     AssemblyCulture
    -0.44
    waarde
    -0.43
    InitVars
    -0.40
    basicConfig
    -0.40
    SharedDtor
    -0.40
    rikt
    -0.39
    POSITIVE LOGITS
     manipulations
    1.06
     manipulation
    1.02
     managing
    0.98
     operations
    0.95
     handling
    0.95
     manipulating
    0.94
     manage
    0.92
     manipulate
    0.91
     management
    0.88
     manip
    0.88
    Activations Density 0.056%

    No Known Activations