© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14949
    Prev
    Next
    INDEX
    Explanations

    elements of programming code and user interface components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vermogen
    -0.33
     liggen
    -0.29
     PyTuple
    -0.28
    вест
    -0.27
     bestaan
    -0.27
    fastjson
    -0.26
     vergeten
    -0.26
     geha
    -0.26
     Kesehatan
    -0.26
    )++;
    -0.26
    POSITIVE LOGITS
    istoitu
    0.72
    isContained
    0.72
    DispatchToProps
    0.68
    oredCriteria
    0.63
     Infórmanos
    0.62
     hObject
    0.61
     ModelExpression
    0.60
    expandindo
    0.60
    NOWLEDG
    0.59
    XmlAccessType
    0.59
    Activations Density 0.154%

    No Known Activations