© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 1149
    Prev
    Next
    INDEX
    Explanations

    mentions of software versioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 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
     InputDecoration
    -0.79
    avajillas
    -0.76
    çalves
    -0.74
     makeStyles
    -0.73
    ulents
    -0.68
    delaire
    -0.67
    déric
    -0.67
    ungkinan
    -0.67
    gley
    -0.67
    >");
    -0.66
    POSITIVE LOGITS
     VERSION
    1.55
     Version
    1.52
     versions
    1.50
     version
    1.49
    Version
    1.44
    VERSION
    1.38
    version
    1.36
     Versions
    1.28
     getVersion
    1.23
    getVersion
    1.18
    Activations Density 0.130%

    No Known Activations