Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13419
    Prev
    Next
    INDEX
    Explanations

    elements of competition within the context of chess

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    CGRectMake
    -0.70
    uxxxx
    -0.68
    didSet
    -0.67
     bezeichneter
    -0.63
    Siren
    -0.56
    Przeczytaj
    -0.56
    SharedDtor
    -0.54
     OFDb
    -0.54
    BUCKET
    -0.52
     AspNetCore
    -0.52
    POSITIVE LOGITS
     chess
    1.10
     Chess
    1.01
    Chess
    0.96
    chess
    0.88
     Fide
    0.81
    棋
    0.74
     Schach
    0.72
     шах
    0.71
    ♟
    0.69
     tournament
    0.68
    Activations Density 0.065%

    No Known Activations