© 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. 11-GEMMASCOPE-RES-16K
    11. 11994
    Prev
    Next
    INDEX
    Explanations

    references to useful information or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <h1>
    -0.46
     Birk
    -0.38
     millioner
    -0.35
    ↵
    -0.35
     tanggung
    -0.33
     supuestamente
    -0.33
     saira
    -0.32
     Schles
    -0.32
    impan
    -0.32
     privado
    -0.31
    POSITIVE LOGITS
     Useful
    1.66
     useful
    1.65
    useful
    1.59
    Useful
    1.59
     usefulness
    1.37
     útiles
    1.34
     utile
    1.32
     helpful
    1.28
     útil
    1.26
    helpful
    1.21
    Activations Density 0.126%

    No Known Activations