© 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. 38-GEMMASCOPE-RES-16K
    11. 16136
    Prev
    Next
    INDEX
    Explanations

    quantitative data and comparisons within clinical studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dessutom
    -0.50
    ambién
    -0.48
    ſchaft
    -0.43
     zwey
    -0.43
    teins
    -0.42
    majánló
    -0.42
    postolic
    -0.41
    cerned
    -0.41
     estadounid
    -0.40
    retudo
    -0.40
    POSITIVE LOGITS
     vs
    3.72
     versus
    3.61
     Versus
    2.81
     Vs
    2.78
    versus
    2.77
     VS
    2.58
    vs
    2.55
    Versus
    2.22
    VS
    1.87
     verses
    1.80
    Activations Density 1.445%

    No Known Activations