© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12933
    Prev
    Next
    INDEX
    Explanations

    references to statistical data or values in the context of medical research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Numbers followed by a decimal point

    np_acts-logits-general · gemini-2.0-flash

    numerical data values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     returned
    -0.38
    UserDTO
    -0.38
    hematical
    -0.36
     vyp
    -0.34
     refunded
    -0.34
     {{{
    -0.33
     hinaus
    -0.32
    บรร
    -0.32
    <!--[
    -0.32
    犹
    -0.32
    POSITIVE LOGITS
    styleType
    0.82
     AssemblyTitle
    0.57
     ModelExpression
    0.55
    tonsoft
    0.54
     AssemblyCompany
    0.54
    AntiForgeryToken
    0.53
     useParams
    0.51
    HtmlAttribute
    0.51
    tagHelperRunner
    0.50
    rungsseite
    0.50
    Activations Density 1.261%

    No Known Activations