© 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. 31-GEMMASCOPE-RES-16K
    11. 5745
    Prev
    Next
    INDEX
    Explanations

    historical events involving diplomatic agreements and conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    historical dates and specific years in chronological narratives.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ніципалі
    -0.84
     queſta
    -0.81
     Gallimard
    -0.80
    SharedDtor
    -0.80
    iſchen
    -0.79
    httphttps
    -0.79
    ðsíða
    -0.78
     garages
    -0.76
    <unused8>
    -0.75
    <unused52>
    -0.75
    POSITIVE LOGITS
     Victorian
    0.47
    Victorian
    0.32
     Crimean
    0.30
     luto
    0.29
     ۱۸
    0.29
     Victoria
    0.26
     tới
    0.26
    PyTuple
    0.25
     steam
    0.23
    ="#"
    0.23
    Activations Density 0.705%

    No Known Activations