© 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. 10-GEMMASCOPE-RES-16K
    6. 13296
    Prev
    Next
    INDEX
    Explanations

    terms related to medical studies and health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.54
    libft
    -0.32
     terang
    -0.30
     Nacionales
    -0.30
     Khusus
    -0.30
    AndEndTag
    -0.30
     محفوظة
    -0.29
     pilas
    -0.29
     vlak
    -0.28
     ועד
    -0.28
    POSITIVE LOGITS
     BorderSide
    0.68
    rungsseite
    0.61
    styleType
    0.60
    AddTagHelper
    0.59
    yAxis
    0.56
     AssemblyCulture
    0.55
     bowiem
    0.55
    featureID
    0.53
     CTL
    0.52
     Lava
    0.51
    Activations Density 11.616%

    No Known Activations