© 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. 9637
    Prev
    Next
    INDEX
    Explanations

    terms associated with health or medical conditions and biological 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
    ので
    -0.58
    ا
    -0.52
    a
    -0.50
    able
    -0.50
    in
    -0.45
    ability
    -0.42
    ao
    -0.40
    amaz
    -0.40
    an
    -0.40
    are
    -0.40
    POSITIVE LOGITS
    med
    0.64
    mable
    0.63
    mers
    0.62
    mmm
    0.58
    ming
    0.58
    ization
    0.55
    soever
    0.53
    MING
    0.53
    mler
    0.52
    iliar
    0.52
    Activations Density 1.264%

    No Known Activations