© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15781
    Prev
    Next
    INDEX
    Explanations

    elements of satire and dialogue, especially in a conversational format

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

    dialogue, satire, and discussions

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects conversational or dialogue-style writing and markers of satire/sarcasm (e.g., words signaling dialogue, conversation, satire, or sarcastic tone).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    -0.53
    Espèce
    -0.40
    tagHelperRunner
    -0.39
    PreferredItem
    -0.38
     poved
    -0.38
    educt
    -0.37
     للاسماء
    -0.37
    \{\\
    -0.37
    strator
    -0.37
     urod
    -0.36
    POSITIVE LOGITS
     Houſe
    0.57
     dialogue
    0.51
    dialogue
    0.50
     dialog
    0.50
     Majefty
    0.48
     imaginary
    0.47
     Anſ
    0.46
    Dialogue
    0.46
     houſe
    0.44
    ſelf
    0.44
    Activations Density 0.232%

    No Known Activations