© 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. 64990
    Prev
    Next
    INDEX
    Explanations

    components and structures related to programming and data handling in code

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

    database, distribution, variables, menu, datasets, form, lifecycle, decoder

    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
     Normdatei
    -0.63
    ftagPool
    -0.55
    ArrowToggle
    -0.51
    TokenNameLPAREN
    -0.49
    +#+#
    -0.46
     IBOutlet
    -0.46
    UserScript
    -0.45
     linkovi
    -0.40
     виправивши
    -0.39
    دانشنامهٔ
    -0.39
    POSITIVE LOGITS
    帖最后由
    0.50
     Verpflichtung
    0.47
     économies
    0.45
    NOPQRST
    0.44
     discusión
    0.43
     rigue
    0.43
     nying
    0.41
    Ữ
    0.41
     nale
    0.41
     Auff
    0.41
    Activations Density 0.097%

    No Known Activations