© 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. 31-GEMMASCOPE-RES-16K
    11. 10141
    Prev
    Next
    INDEX
    Explanations

    phrases related to recruitment and participation in studies or interviews

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

    numerical estimates and measurements presented with quantitative values.

    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
     przecież
    -0.29
    KindOfClass
    -0.27
     erfolgreichen
    -0.26
    からの
    -0.26
    nameof
    -0.26
    まさかの
    -0.26
    わざわざ
    -0.26
    Inset
    -0.26
    逆に
    -0.25
    今後の
    -0.25
    POSITIVE LOGITS
     approximately
    2.09
     Approximately
    1.80
     roughly
    1.80
    Approximately
    1.78
    approximately
    1.78
     approx
    1.75
     aproximadamente
    1.70
     примерно
    1.69
    大約
    1.56
     Approx
    1.55
    Activations Density 1.281%

    No Known Activations