© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2708
    Prev
    Next
    INDEX
    Explanations

    instances of personal reflection and emotional experiences

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

    introspective passages where the narrator reflects on their inner thoughts, feelings, and personal concerns.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.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
    GEBURTSDATUM
    -0.62
    WebVitals
    -0.62
     propOrder
    -0.60
     Italijani
    -0.57
     BoxFit
    -0.54
    saraba
    -0.53
     AttributeSet
    -0.53
    IsContent
    -0.52
    醐
    -0.52
    pushFollow
    -0.50
    POSITIVE LOGITS
     thoughts
    2.20
     thought
    1.93
    thoughts
    1.83
     thinking
    1.74
     Thoughts
    1.73
    Thoughts
    1.67
    thought
    1.63
     THOUGHTS
    1.55
    thinking
    1.55
     Thought
    1.54
    Activations Density 0.273%

    No Known Activations