© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 10100
    Prev
    Next
    INDEX
    Explanations

    language related to mathematical proof and analysis

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

    finding 'for'

    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
    DrawerToggle
    -0.55
    RegressionTest
    -0.52
    UnusedPrivate
    -0.51
     nakalista
    -0.47
    évaluateur
    -0.46
    AutoresizingMask
    -0.46
    DockStyle
    -0.45
    RTLR
    -0.45
    GetAxis
    -0.44
    tagHelperRunner
    -0.43
    POSITIVE LOGITS
     for
    0.98
    对于
    0.68
     для
    0.65
    Untuk
    0.63
     برای
    0.63
     untuk
    0.63
    for
    0.62
     Untuk
    0.61
     For
    0.60
    對於
    0.60
    Activations Density 0.853%

    No Known Activations