© 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. 82695
    Prev
    Next
    INDEX
    Explanations

    references to recent advancements or changes in various fields

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

    new developments

    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
    xbf
    -0.35
    eney
    -0.34
    UrlResolution
    -0.34
    čít
    -0.32
    uy
    -0.32
    multirow
    -0.32
     calendar
    -0.31
    urismo
    -0.31
    itsch
    -0.31
     calendars
    -0.31
    POSITIVE LOGITS
     developments
    0.98
     Developments
    0.90
     development
    0.75
    Development
    0.73
     Development
    0.71
     Entwicklung
    0.71
    develop
    0.71
    Entwicklung
    0.69
    development
    0.69
     Desenvolvimento
    0.67
    Activations Density 0.030%

    No Known Activations