© 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. 23-GEMMASCOPE-RES-16K
    11. 3775
    Prev
    Next
    INDEX
    Explanations

    specific terminology associated with models, strains, and editions in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Италијани
    -0.58
    ỡng
    -0.53
    AutoScaleMode
    -0.46
     MainAxisSize
    -0.45
     pinulongan
    -0.44
    tagHelperRunner
    -0.43
     assurent
    -0.42
    Ƚ
    -0.42
    IntoConstraints
    -0.42
     själva
    -0.41
    POSITIVE LOGITS
     edition
    0.74
     editions
    0.62
     EDITION
    0.61
    Edition
    0.59
     copy
    0.58
     Edition
    0.58
    edition
    0.56
     versions
    0.56
     copies
    0.56
     version
    0.55
    Activations Density 1.044%

    No Known Activations