© 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. 38-GEMMASCOPE-RES-16K
    11. 15074
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurements and statistical analysis

    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
     informée
    -0.39
    Източници
    -0.36
    agisse
    -0.32
    Composable
    -0.32
    aarrggbb
    -0.30
     Tik
    -0.30
    DriverManager
    -0.30
    </thead>
    -0.29
    ướng
    -0.29
    Бележки
    -0.28
    POSITIVE LOGITS
    ity
    1.44
    ities
    1.34
     ity
    1.32
    ITY
    1.25
    ty
    1.23
    itys
    1.14
    lty
    1.12
     ty
    1.10
    TY
    1.07
    uty
    1.05
    Activations Density 0.594%

    No Known Activations