© 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. 15836
    Prev
    Next
    INDEX
    Explanations

    references to skin and its characteristics related to health and identity

    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
    Personensuche
    -0.45
    devamını
    -0.41
    ContentAlignment
    -0.40
     nonUne
    -0.39
     noDo
    -0.39
     astore
    -0.39
    sword
    -0.39
     HasFactory
    -0.38
     piring
    -0.37
    shaft
    -0.35
    POSITIVE LOGITS
     skin
    3.20
     Skin
    2.64
    skin
    2.59
    Skin
    2.55
     SKIN
    2.42
     skins
    2.31
    SKIN
    2.16
     peau
    2.05
    皮肤
    1.96
     Skins
    1.94
    Activations Density 0.400%

    No Known Activations