Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 97576
    Prev
    Next
    INDEX
    Explanations

    actions and movements related to grappling and position control in combat sports

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

    positions in fighting or mechanics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebElementEntity
    -0.71
    PMailer
    -0.65
    يكب
    -0.50
     sumpay
    -0.50
    Дереккөздер
    -0.49
    adaptiveStyles
    -0.49
    principalColumn
    -0.47
     rallying
    -0.46
     noDo
    -0.45
     firebaseConfig
    -0.45
    POSITIVE LOGITS
     Dabei
    0.37
    BeforeMethod
    0.35
    Closeable
    0.34
    Доброго
    0.34
    Fprintf
    0.34
     wobei
    0.34
    Clave
    0.32
    ckså
    0.32
     '{@
    0.31
    OptionPane
    0.31
    Activations Density 0.235%

    No Known Activations