Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 128358
    Prev
    Next
    INDEX
    Explanations

    occurrences of source identifiers and related API request fields

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

    source mac address

    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
     Италијани
    -0.59
    enumi
    -0.52
     EconPapers
    -0.52
     utafitiHapana
    -0.50
    ighborhood
    -0.48
     HttpNotFound
    -0.48
    Gön
    -0.48
     للمعارف
    -0.48
     wireType
    -0.47
    ロウィン
    -0.46
    POSITIVE LOGITS
     source
    0.81
     Source
    0.80
    source
    0.73
    Source
    0.73
     sources
    0.71
     SOURCE
    0.66
     源
    0.65
     Sources
    0.64
     sourcing
    0.63
    源
    0.63
    Activations Density 0.011%

    No Known Activations