© 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. 13263
    Prev
    Next
    INDEX
    Explanations

    concepts related to compactness or compact design

    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
     للاسماء
    -0.70
     CommandType
    -0.64
    twimg
    -0.61
    bootstrapcdn
    -0.60
     Normdatei
    -0.57
     Thumbnails
    -0.57
    BagConstraints
    -0.56
     camry
    -0.55
    majánló
    -0.54
     plexus
    -0.52
    POSITIVE LOGITS
     fictional
    0.69
     fiction
    0.69
    fic
    0.59
     ficción
    0.56
     fictitious
    0.54
     FICTION
    0.53
     imaginary
    0.52
     hypothetical
    0.52
     imaginative
    0.50
    sp
    0.49
    Activations Density 0.269%

    No Known Activations