© 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. 37-GEMMASCOPE-RES-16K
    11. 8233
    Prev
    Next
    INDEX
    Explanations

    terms related to measurement, counting, and evaluation within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.69
    SourceChecksum
    -0.66
     disambiguazione
    -0.66
     Paglinawan
    -0.65
     дописавши
    -0.65
     върху
    -0.62
     autorytatywna
    -0.59
    parsedMessage
    -0.56
     ujednoznacz
    -0.52
     ProtoMessage
    -0.52
    POSITIVE LOGITS
     On
    2.48
    On
    2.28
     ON
    1.95
    オン
    1.55
    ON
    1.53
    on
    1.52
     on
    1.47
     onsite
    1.45
     オン
    1.38
    OnThe
    1.16
    Activations Density 1.045%

    No Known Activations