© 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. 35-GEMMASCOPE-RES-16K
    11. 5932
    Prev
    Next
    INDEX
    Explanations

    comparative phrases or expressions that highlight differences between items or concepts

    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
    除了
    -0.43
     related
    -0.36
    除
    -0.34
     selain
    -0.34
    あらゆる
    -0.34
    各
    -0.33
     wszel
    -0.33
     various
    -0.33
     egyéb
    -0.32
    //
    -0.32
    POSITIVE LOGITS
     others
    3.55
    Others
    3.33
     Others
    3.33
    others
    3.14
     OTHERS
    2.81
    OTHERS
    2.00
     دیگران
    1.93
     אחרים
    1.50
    别人
    1.48
    別人
    1.45
    Activations Density 0.683%

    No Known Activations