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. 31-GEMMASCOPE-RES-131K
    6. 12948
    Prev
    Next
    INDEX
    Explanations

    phrases that express opinions or reactions to experiences or sounds

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

    how something sounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Miel
    -0.40
     hué
    -0.37
     dedicado
    -0.36
     HttpNotFound
    -0.36
     gabbana
    -0.35
     vean
    -0.34
     sentado
    -0.33
     kimse
    -0.33
     restantes
    -0.33
    مراجع
    -0.32
    POSITIVE LOGITS
     Sounds
    0.90
    Sounds
    0.88
     sounds
    0.84
     sounded
    0.79
     sounding
    0.79
     Sound
    0.78
     SOUND
    0.78
     sound
    0.77
    Sound
    0.76
    sounds
    0.72
    Activations Density 0.006%

    No Known Activations