© 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. 4871
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data management and metadata concepts

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

    technical and scientific terminology related to physics experiments and detector systems.

    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
     peito
    -0.33
     salão
    -0.33
     zdrowia
    -0.33
     culturelle
    -0.32
    azgo
    -0.30
     skills
    -0.30
     desconhe
    -0.30
     penas
    -0.29
    deelte
    -0.29
     alimentaires
    -0.29
    POSITIVE LOGITS
    İstinadlar
    0.56
     ddelweddau
    0.54
     الرياضيه
    0.53
     propOrder
    0.53
    Бахар
    0.52
     nahilalakip
    0.52
    twimg
    0.50
     חיצוניים
    0.49
    posedge
    0.49
    لينكات
    0.49
    Activations Density 0.305%

    No Known Activations