© 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. 35-GEMMASCOPE-RES-16K
    11. 4729
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistical information related to sports and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     THOUS
    -0.59
     thousand
    -0.56
     Hundreds
    -0.54
    Thousand
    -0.52
     Thousands
    -0.52
    новништво
    -0.52
     Thousand
    -0.51
     centenary
    -0.49
    Hundreds
    -0.49
     HUND
    -0.48
    POSITIVE LOGITS
     twenty
    1.33
     Twenty
    1.20
     thirty
    1.20
    Twenty
    1.18
    二十
    1.06
    twenty
    1.06
     Thirty
    1.04
    Thirty
    1.02
     TWENTY
    1.00
    三十
    0.93
    Activations Density 1.877%

    No Known Activations