© 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. 38-GEMMASCOPE-RES-16K
    6. 9880
    Prev
    Next
    INDEX
    Explanations

    high-value statistics and measurements related to research findings

    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
     Vergrößern
    -0.38
    bootstrapcdn
    -0.38
    Twelve
    -0.33
    isible
    -0.33
    consulté
    -0.33
    ató
    -0.33
    ashian
    -0.32
    chó
    -0.32
     ATS
    -0.31
    xFFFFFFFF
    -0.31
    POSITIVE LOGITS
     ninety
    1.20
     Ninety
    1.13
     eighty
    1.07
     Eighty
    0.98
     seventy
    0.93
     Seventy
    0.90
    9
    0.72
    ighty
    0.72
    百分之
    0.67
     ۹
    0.62
    Activations Density 1.333%

    No Known Activations