© 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. 6941
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns and references to identifiable entities

    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
    ه
    -1.34
    zelfde
    -1.05
    y
    -1.02
    ی
    -1.01
    ி
    -0.96
    ה
    -0.94
    ي
    -0.90
    ി
    -0.89
    o
    -0.83
    ी
    -0.81
    POSITIVE LOGITS
    <bos>
    0.99
    juries
    0.56
    notated
    0.49
    %;">
    0.45
    JKLM
    0.44
    🤣🤣
    0.43
    pośred
    0.42
    ۰۰
    0.40
    près
    0.40
    scen
    0.39
    Activations Density 2.713%

    No Known Activations