© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11342
    Prev
    Next
    INDEX
    Explanations

    terms related to procedures, processes, and mechanisms in technical contexts

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

    preceding "process," "mechanism," "procedure," or "capabilities"

    np_acts-logits-general · gemini-2.0-flash

    system procedures and capabilities

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    нодоро
    -0.48
    '>
    -0.47
     intptr
    -0.47
    '}),
    -0.46
    
    -0.46
    "},
    -0.46
    '})
    -0.45
    '},
    -0.45
     macho
    -0.43
     bezeichneter
    -0.43
    POSITIVE LOGITS
    SpringRunner
    0.57
    addCriterion
    0.53
     typelib
    0.51
    providedIn
    0.51
     intStringLen
    0.50
    TemporalType
    0.47
    IntoConstraints
    0.47
    transQ
    0.46
     AssemblyCulture
    0.45
    ungsbedingungen
    0.43
    Activations Density 1.683%

    No Known Activations