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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 55378
    Prev
    Next
    INDEX
    Explanations

    phrases reflecting uncertainty and contemplation

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

    at this moment

    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
     sociali
    -0.37
     annuel
    -0.36
     Sábado
    -0.34
     retrô
    -0.33
    ordenadas
    -0.33
     anteriore
    -0.33
     strá
    -0.33
    Sábado
    -0.33
     günstig
    -0.32
     sábado
    -0.32
    POSITIVE LOGITS
     currently
    0.89
     сейчас
    0.80
    currently
    0.80
     presently
    0.78
     now
    0.77
     Currently
    0.77
    Currently
    0.76
     momentan
    0.73
     Presently
    0.70
     derzeit
    0.69
    Activations Density 0.068%

    No Known Activations