© 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. 12638
    Prev
    Next
    INDEX
    Explanations

    concepts related to complex systems or structures

    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
    findpost
    -0.66
     незавершена
    -0.61
     referenties
    -0.57
     hObject
    -0.57
     utafitiHapana
    -0.56
     ControllerBase
    -0.56
    endsection
    -0.55
     onPostExecute
    -0.54
    astify
    -0.53
     numberWith
    -0.52
    POSITIVE LOGITS
     Gestaltung
    0.40
     complexity
    0.38
     style
    0.38
    libft
    0.37
     strategic
    0.37
     scalability
    0.36
     concept
    0.36
     Marín
    0.36
     flexibility
    0.36
     Beweg
    0.35
    Activations Density 1.878%

    No Known Activations