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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 130011
    Prev
    Next
    INDEX
    Explanations

    statements or affirmations emphasizing certainty and belief

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

    contrasting ideas or statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otherwise
    -0.40
     specific
    -0.39
     currently
    -0.38
     jinak
    -0.35
     specifics
    -0.33
    还不错
    -0.33
    共有
    -0.33
     depending
    -0.33
    specific
    -0.32
     satisfactorily
    -0.32
    POSITIVE LOGITS
    instead
    0.93
    Instead
    0.91
     invece
    0.87
    Worse
    0.86
     instead
    0.86
     Instead
    0.84
     kasarigan
    0.83
    ftagPool
    0.82
     Worse
    0.81
    Dabei
    0.78
    Activations Density 0.022%

    No Known Activations