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

    Neuronpedia

    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
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11558
    Prev
    Next
    INDEX
    Explanations

    expressions of thought and questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.46
    LLocation
    -0.35
    intios
    -0.34
    见状
    -0.33
    ttemberg
    -0.33
    XtraReports
    -0.32
    styleType
    -0.32
    WebVitals
    -0.32
     AttributeSet
    -0.32
    AnchorStyles
    -0.32
    POSITIVE LOGITS
     thinking
    3.06
     thought
    2.81
    thinking
    2.73
     Thinking
    2.70
    Thinking
    2.67
     thoughts
    2.63
    thought
    2.50
     think
    2.47
     THINK
    2.45
     Think
    2.39
    Activations Density 0.632%

    No Known Activations