© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 5507
    Prev
    Next
    INDEX
    Explanations

    references to specific substances and their effects or properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/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.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -1.04
    ↵↵
    -1.00
     \&
    -0.60
    ↵↵↵
    -0.58
     longterm
    -0.52
     $\%
    -0.51
     \#
    -0.50
    ResId
    -0.50
     //$
    -0.50
     \%
    -0.50
    POSITIVE LOGITS
    <h2>
    1.75
    <h3>
    1.66
    <h4>
    1.52
    <blockquote>
    1.48
    <h1>
    1.47
    <h5>
    1.34
    <h6>
    1.27
    <strong>
    1.18
    *
    1.08
    <b>
    0.98
    Activations Density 1.868%

    No Known Activations