© 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. 5458
    Prev
    Next
    INDEX
    Explanations

    references to previous works, findings, and success in publications or announcements

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

    existing results or work

    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
    RenderAtEndOf
    -0.52
    ArgsConstructor
    -0.47
     lenker
    -0.44
    mobileqq
    -0.41
    webElementXpaths
    -0.40
    oldest
    -0.39
     المعيارى
    -0.39
    ContentAsync
    -0.38
    UrlResolution
    -0.38
     刺繍
    -0.37
    POSITIVE LOGITS
     bestehende
    0.44
     existing
    0.43
    Already
    0.42
    áját
    0.42
    arashtra
    0.42
     already
    0.42
     étoient
    0.42
     ohnehin
    0.41
     للاسماء
    0.40
     Already
    0.40
    Activations Density 0.237%

    No Known Activations