© 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. 38019
    Prev
    Next
    INDEX
    Explanations

    references to state changes or updates in an event-driven programming context

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

    changed value event

    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
     ویکی‌پدی
    -0.72
    parsedMessage
    -0.69
    الإنجليزية
    -0.68
     للاسماء
    -0.65
    __':
    -0.64
     doubtnut
    -0.62
    NameInMap
    -0.61
    CppMethod
    -0.61
     IBOutlet
    -0.60
    isContained
    -0.60
    POSITIVE LOGITS
    ness
    0.35
     meyd
    0.30
    nervous
    0.29
     telef
    0.29
    VALID
    0.29
    Changed
    0.28
    nya
    0.28
     Broder
    0.28
    priv
    0.26
     doğ
    0.26
    Activations Density 0.005%

    No Known Activations