© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 39-GEMMASCOPE-RES-16K
    11. 2193
    Prev
    Next
    INDEX
    Explanations

    specific identifiers and numeric values associated with legal terms or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seventeenth
    -0.44
     Infórmanos
    -0.41
     rhestr
    -0.35
    RefNanny
    -0.34
    EDEFAULT
    -0.32
     Seventeenth
    -0.32
     Seventeen
    -0.32
    الثة
    -0.32
    inSlope
    -0.31
    impresa
    -0.30
    POSITIVE LOGITS
    8
    1.72
     Eight
    1.68
     eight
    1.66
    八
    1.44
    Eight
    1.44
     Eighth
    1.44
     EIGHT
    1.41
     eighth
    1.41
     вось
    1.39
     ocho
    1.36
    Activations Density 2.642%

    No Known Activations