© 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. 3466
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preferences and desires related to learning and self-improvement

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

    first-person perspective and subjective observations or experiences.

    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
    出版年
    -0.71
    awtextra
    -0.66
     <<<<<<<<<<<<<<
    -0.64
    httphttps
    -0.50
    Geplaatst
    -0.48
    expandindo
    -0.48
    ftagPool
    -0.47
    jsxFileName
    -0.47
    setObjectName
    -0.45
     invokingState
    -0.45
    POSITIVE LOGITS
     seeing
    2.34
     saw
    2.14
     sees
    2.06
     see
    1.94
     seen
    1.84
     Seeing
    1.82
    seeing
    1.79
    Seeing
    1.73
     melihat
    1.70
    saw
    1.55
    Activations Density 0.681%

    No Known Activations