© 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. 14-GEMMASCOPE-RES-16K
    11. 6301
    Prev
    Next
    INDEX
    Explanations

    identifiers and keywords related to problems in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onOptions
    -0.40
     informaciones
    -0.38
     provisoire
    -0.37
     democrática
    -0.37
     zainteres
    -0.35
     quirúrg
    -0.33
     Demokratie
    -0.33
     extranjera
    -0.33
     nadzieję
    -0.33
     démocratique
    -0.33
    POSITIVE LOGITS
    TintMode
    0.69
    انجليز
    0.66
    OGND
    0.65
     betweenstory
    0.63
    TagMode
    0.62
     BorderRadius
    0.60
    Tikang
    0.59
    SuppressLint
    0.59
     snippetHide
    0.59
     Exercise
    0.57
    Activations Density 0.167%

    No Known Activations