© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 12592
    Prev
    Next
    INDEX
    Explanations

    elements of structured data, specifically focusing on keys, values, and their relationships within a data format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.90
    SourceChecksum
    -0.84
    bootstrapcdn
    -0.78
    SequentialGroup
    -0.73
    MigrationBuilder
    -0.73
    IntoConstraints
    -0.72
    Personendaten
    -0.72
     Infórmanos
    -0.72
    <unused23>
    -0.72
    contentLoaded
    -0.72
    POSITIVE LOGITS
     <
    0.97
    <
    0.94
     $\
    0.63
    ><
    0.49
    《
    0.46
    $\
    0.39
     [
    0.37
    <u>
    0.37
    an
    0.36
     $
    0.36
    Activations Density 0.288%

    No Known Activations