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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 38950
    Prev
    Next
    INDEX
    Explanations

    instances of questioning or doubt related to personal beliefs and situations

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

    asking questions about why

    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
     للاسماء
    -0.75
     BoxDecoration
    -0.75
    httphttps
    -0.69
     InputDecoration
    -0.63
     Houſe
    -0.60
    majánló
    -0.59
    XmlAccessType
    -0.59
    InjectAttribute
    -0.58
    Datuak
    -0.56
     imagui
    -0.56
    POSITIVE LOGITS
     questioning
    1.20
     questioned
    1.18
     cuestion
    0.93
     Question
    0.91
    question
    0.81
     question
    0.76
    Question
    0.75
     QUESTION
    0.75
     questionable
    0.74
    质疑
    0.67
    Activations Density 0.012%

    No Known Activations