© 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. 20-GEMMASCOPE-RES-131K
    11. 53146
    Prev
    Next
    INDEX
    Explanations

    terms related to control systems and their operations

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

    control and its functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Merz
    -0.40
    ifax
    -0.38
    yeth
    -0.35
    newtheorem
    -0.35
    addAttribute
    -0.35
    Webpack
    -0.34
    Non
    -0.34
    toastr
    -0.33
    addHeader
    -0.33
    Beijo
    -0.33
    POSITIVE LOGITS
     control
    0.77
     Control
    0.73
     Steuerung
    0.72
    controlling
    0.72
     CONTROL
    0.72
    control
    0.71
     Majefty
    0.69
     controls
    0.68
     controlling
    0.68
    DispatchToProps
    0.67
    Activations Density 0.039%

    No Known Activations