© 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. 91174
    Prev
    Next
    INDEX
    Explanations

    constructs related to grammatical structure and modality in language

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

    file access and permissions

    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
    TagMode
    -0.74
    CopyWith
    -0.73
     Taktlose
    -0.72
     ویکی‌پدی
    -0.71
    OGND
    -0.71
    GEBURTSDATUM
    -0.71
    ✨:
    -0.69
    хьтан
    -0.68
    rawDesc
    -0.68
     dieſes
    -0.65
    POSITIVE LOGITS
     actually
    0.71
     already
    0.65
     nevertheless
    0.63
     also
    0.60
     necessarily
    0.59
     ultimately
    0.59
     finally
    0.59
     suddenly
    0.58
     unfortunately
    0.58
     eventually
    0.57
    Activations Density 0.005%

    No Known Activations