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

    Neuronpedia

    Jacobian LensNEW
    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. 16035
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and syntactical elements in text

    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
    s
    -0.52
    MethodManager
    -0.32
     Wikiseite
    -0.30
    的
    -0.29
    ς
    -0.29
    лактика
    -0.28
    ịch
    -0.28
    ների
    -0.27
    ים
    -0.27
    getLogger
    -0.26
    POSITIVE LOGITS
     kasarigan
    0.85
    ::::::::::::::::
    0.80
    ::::
    0.72
    页面存档备份
    0.68
    tonsoft
    0.65
     wireType
    0.65
    出版年
    0.65
     OMITBAD
    0.64
    :::
    0.64
    MLLoader
    0.63
    Activations Density 0.241%

    No Known Activations