© 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. 14264
    Prev
    Next
    INDEX
    Explanations

    commands or requests for action

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

    imperatives or commands that tell someone to leave or go away.

    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
    amitié
    -0.45
     بتوان
    -0.43
    mappedBy
    -0.40
     nemlig
    -0.40
     akurat
    -0.39
     potentially
    -0.38
    Quite
    -0.38
    jsdelivr
    -0.38
    ことを
    -0.37
    omentos
    -0.37
    POSITIVE LOGITS
     yourselves
    0.57
     protoimpl
    0.51
     thyself
    0.50
    請繼續往下閱讀
    0.47
     ostavi
    0.47
     please
    0.45
     thy
    0.44
    phemy
    0.42
    رشف
    0.42
    TokenNameLBRACE
    0.42
    Activations Density 0.216%

    No Known Activations