© 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. 10-GEMMASCOPE-RES-16K
    11. 8770
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to optimization and problem-solving in computational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seamnă
    -0.43
    </thead>
    -0.38
    bigl
    -0.35
    值的
    -0.30
     riot
    -0.30
     midway
    -0.29
    ahrt
    -0.29
     Fav
    -0.29
     vital
    -0.28
     establishment
    -0.28
    POSITIVE LOGITS
    makeConstraints
    0.68
     ConstraintSet
    0.66
     optimization
    0.66
    IntoConstraints
    0.65
    fromnode
    0.64
     Optimization
    0.63
    psack
    0.61
    הערות
    0.61
    Planning
    0.60
    Optimal
    0.59
    Activations Density 0.872%

    No Known Activations