© 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. 35-GEMMASCOPE-RES-16K
    11. 7478
    Prev
    Next
    INDEX
    Explanations

    references to legal or jurisdictional limits and boundaries

    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
    inheritdoc
    -0.39
     thiệu
    -0.38
    atisk
    -0.33
    -0.32
     ngược
    -0.31
    NewGuid
    -0.30
     tamam
    -0.29
     hàng
    -0.29
     milliers
    -0.28
     hand
    -0.28
    POSITIVE LOGITS
     bounds
    1.57
     boundaries
    1.55
     scope
    1.48
     confines
    1.46
     Boundaries
    1.28
    boundaries
    1.27
     limits
    1.25
     borders
    1.23
     Bounds
    1.20
     purview
    1.18
    Activations Density 0.497%
    No Known Activations