© 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. 110864
    Prev
    Next
    INDEX
    Explanations

    actions related to throwing or hurling objects

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

    throwing or hurling objects

    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
    UTERS
    -0.55
    Atsauces
    -0.51
    viewWillAppear
    -0.50
    BibitemShut
    -0.50
     snippetHide
    -0.49
    ApplicationTests
    -0.49
    Pautan
    -0.48
     επισ
    -0.48
    xymatrix
    -0.47
    참고
    -0.47
    POSITIVE LOGITS
     objects
    0.56
     items
    0.50
     cups
    0.49
     insults
    0.48
     bags
    0.48
     books
    0.47
     stones
    0.46
     papers
    0.46
     coffee
    0.46
     eggs
    0.45
    Activations Density 0.018%

    No Known Activations