© 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. 9-GEMMASCOPE-RES-131K
    11. 38293
    Prev
    Next
    INDEX
    Explanations

    keywords and commands associated with programming and coding in various languages and libraries

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

    PositiveButton, encodeWithCoder, sql

    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
     Injectable
    -0.63
     snippetHide
    -0.55
    stateProvider
    -0.51
     disambiguazione
    -0.50
    queryInterface
    -0.49
    parametrize
    -0.48
    DllImport
    -0.47
    MockBean
    -0.45
    providedIn
    -0.44
    ExceptionHandler
    -0.44
    POSITIVE LOGITS
    UseVisualStyle
    0.69
    setAction
    0.68
     مواليد
    0.68
    Архівовано
    0.68
     BitmapFactory
    0.66
     actionMode
    0.65
    getAction
    0.60
     ContentValues
    0.58
    </tfoot>
    0.57
    ByExample
    0.54
    Activations Density 0.001%

    No Known Activations