© 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. 3-GEMMASCOPE-RES-16K
    11. 7211
    Prev
    Next
    INDEX
    Explanations

    structured data elements such as dates, categories, and programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageOf
    -0.85
    ValueStyle
    -0.82
    RegressionTest
    -0.79
    IntoConstraints
    -0.79
     wireType
    -0.76
    +#+#
    -0.76
     IndexPath
    -0.73
    featureID
    -0.73
    ItemBackground
    -0.73
    RectangleBorder
    -0.72
    POSITIVE LOGITS
    addProperty
    0.31
     rather
    0.29
    tfrac
    0.28
    s
    0.27
     âmes
    0.27
    nm
    0.27
    렇
    0.27
     saja
    0.26
    inaldi
    0.26
    <strong>
    0.26
    Activations Density 1.537%

    No Known Activations