© 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. 40-GEMMASCOPE-RES-16K
    11. 7301
    Prev
    Next
    INDEX
    Explanations

    references to medical organizations and legal terms associated with health or software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sal
    -0.75
    san
    -0.73
     san
    -0.70
    sol
    -0.69
    sam
    -0.69
     sal
    -0.69
    shi
    -0.68
    sar
    -0.68
    sab
    -0.68
     sol
    -0.66
    POSITIVE LOGITS
     Ş
    0.51
    Ｓ
    0.50
     Š
    0.49
     Sz
    0.46
     Ս
    0.45
     Ś
    0.44
     Số
    0.44
     Σ
    0.44
     Se
    0.44
     Ș
    0.43
    Activations Density 2.434%

    No Known Activations