© 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. 38745
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword "public" in a programmatic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ⓧ
    -0.36
    例句
    -0.33
    elerik
    -0.31
    QUADS
    -0.30
    ọa
    -0.30
    惮
    -0.29
    gä
    -0.29
     méri
    -0.29
    oredCriteria
    -0.29
    longrightarrow
    -0.28
    POSITIVE LOGITS
    Hozzáférés
    0.73
     autorytatywna
    0.69
     ब्रेकडाउन
    0.66
     فريبيس
    0.64
     <=",
    0.59
    NameInMap
    0.59
    InputTagHelper
    0.58
    parsedMessage
    0.58
    Hentet
    0.57
     Normdatei
    0.57
    Activations Density 0.001%

    No Known Activations