© 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. 38267
    Prev
    Next
    INDEX
    Explanations

    comments and statement terminators in code

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

    comment indicators

    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
     Signalez
    -0.90
    RenderAtEndOf
    -0.87
    MessageTagHelper
    -0.80
    ItemBackground
    -0.75
    +#+#
    -0.75
    setupUi
    -0.73
     disambiguazione
    -0.71
    principalColumn
    -0.71
    XmlAccessorType
    -0.71
    parsedMessage
    -0.69
    POSITIVE LOGITS
     ekster
    0.31
     however
    0.31
     individual
    0.30
     panahon
    0.30
    iteritems
    0.29
     nazwis
    0.29
     autorisation
    0.29
     everything
    0.28
     internal
    0.28
     extracts
    0.27
    Activations Density 0.022%

    No Known Activations