© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13027
    Prev
    Next
    INDEX
    Explanations

    parenthetical information, particularly birth dates and related details

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

    opening parentheses followed by birth dates or biographical information.

    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
     Bewußt
    -0.34
     throughout
    -0.29
    ้อมูล
    -0.29
     intéressant
    -0.27
     akár
    -0.27
     bezeichneter
    -0.27
     cajones
    -0.26
     løpet
    -0.26
     ekor
    -0.25
     either
    -0.25
    POSITIVE LOGITS
     formerly
    1.03
    formerly
    1.02
    Formerly
    0.91
     Formerly
    0.88
    aka
    0.86
    previously
    0.84
    née
    0.83
    addCriterion
    0.81
     renamed
    0.81
    fka
    0.81
    Activations Density 0.408%

    No Known Activations