© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 58504
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components, specifically for dynamic panel interactions

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

    tab and folder

    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
     للاسماء
    -0.56
    hoeddwyd
    -0.48
     createSprite
    -0.48
    HostException
    -0.47
    
    -0.44
     الحره
    -0.44
    Cyfeiriadau
    -0.44
    IntoConstraints
    -0.43
     شناسی
    -0.43
    TypedValue
    -0.42
    POSITIVE LOGITS
    TabPage
    0.67
    GroupBox
    0.67
     groupBox
    0.58
    tabPage
    0.56
    TabStop
    0.54
    groupBox
    0.53
     tabPage
    0.53
    tabControl
    0.47
    portlet
    0.47
    XmlAccessorType
    0.46
    Activations Density 0.134%

    No Known Activations