© 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. 0-GEMMASCOPE-RES-16K
    11. 12971
    Prev
    Next
    INDEX
    Explanations

    references to "single" or "single" items or concepts, as well as their multiplicity or order

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     menye
    -0.49
    πως
    -0.45
     wypo
    -0.41
     parlato
    -0.40
     comprometido
    -0.40
    rippa
    -0.40
     especializado
    -0.40
     sürd
    -0.39
    ability
    -0.39
     mukana
    -0.39
    POSITIVE LOGITS
     single
    0.91
     Single
    0.82
    Single
    0.78
     fixed
    0.76
    single
    0.75
     SINGLE
    0.75
    fix
    0.69
    fixed
    0.66
     fixing
    0.66
     fix
    0.65
    Activations Density 0.253%

    No Known Activations