© 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. 11159
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate confusion and complexity in thoughts and relationships

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

    surrounding

    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
    hyrchwyd
    -0.56
    jsxFileName
    -0.52
    bitField
    -0.51
    OGND
    -0.49
    !*\
    -0.46
    ArgsConstructor
    -0.45
    исленность
    -0.44
    mybatisplus
    -0.43
    テンツ
    -0.43
     TAMBÉM
    -0.42
    POSITIVE LOGITS
     confusing
    1.11
     confusion
    1.08
     confused
    1.04
     confusión
    1.01
     confuse
    1.01
     confuses
    0.98
     Confusion
    0.98
     Confused
    0.96
     confund
    0.94
     confuso
    0.93
    Activations Density 0.060%

    No Known Activations