© 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. 1373
    Prev
    Next
    INDEX
    Explanations

    findings and results related to research and experiments

    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
    verifyException
    -0.51
    helin
    -0.48
     transfieras
    -0.46
    optionalTypeArgs
    -0.46
     ***!
    -0.43
    transQ
    -0.43
     Signalez
    -0.43
    writeFieldEnd
    -0.42
    Schwe
    -0.41
    orylation
    -0.40
    POSITIVE LOGITS
     impressive
    0.43
    Toponymie
    0.42
     amazement
    0.38
     ModelExpression
    0.37
    Там
    0.36
    发现
    0.35
     oil
    0.35
     majority
    0.35
    SourceChecksum
    0.35
     ditem
    0.35
    Activations Density 0.812%

    No Known Activations