© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8955
    Prev
    Next
    INDEX
    Explanations

    operations related to data manipulation and collection processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.32
    けません
    -0.31
    iconque
    -0.31
    RuntimeObject
    -0.30
    unningham
    -0.29
     بگیرید
    -0.29
    }{*}{
    -0.29
    someone
    -0.28
    тесь
    -0.28
    外的
    -0.28
    POSITIVE LOGITS
    ConstraintMaker
    1.18
     незавершена
    0.66
     мәкал
    0.64
    httphttps
    0.63
     jspb
    0.59
     AssemblyTitle
    0.58
    ніципалі
    0.57
     Bourgoin
    0.57
    GOTREF
    0.57
    ResumeLayout
    0.57
    Activations Density 0.389%

    No Known Activations