© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3277
    Prev
    Next
    INDEX
    Explanations

    statements about personal experiences and reflections

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

    the phrase "what it's like" or similar expressions describing subjective experiences or perspectives.

    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
     apapun
    -0.42
     anything
    -0.40
    anything
    -0.39
     Anything
    -0.36
    enapa
    -0.36
    miento
    -0.36
     égard
    -0.35
     qualquer
    -0.34
     Cualquier
    -0.34
     mengapa
    -0.34
    POSITIVE LOGITS
    -------------</
    0.58
     nakalista
    0.53
    
    0.52
    はこんな感じ
    0.52
     prawdzi
    0.52
    ecuted
    0.52
    Koordinaten
    0.52
     wahre
    0.50
     فريبيس
    0.50
     createState
    0.50
    Activations Density 0.129%

    No Known Activations