© 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-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 2035
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the act of resolving or working through issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     描
    -0.60
    nocení
    -0.58
     nahilalakip
    -0.57
    issionais
    -0.57
    cadilly
    -0.55
    arture
    -0.55
    Controllo
    -0.54
     للاسماء
    -0.53
     spades
    -0.53
    mbolos
    -0.53
    POSITIVE LOGITS
     workout
    0.73
     defaultstate
    0.70
    #
    0.67
    //
    0.65
    workout
    0.65
     descobrir
    0.63
    RotationOrder
    0.60
     Workout
    0.59
    Workout
    0.57
     выясни
    0.57
    Activations Density 0.179%

    No Known Activations