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. 9940
    Prev
    Next
    INDEX
    Explanations

    terms related to miniature electrical switches and their mechanisms

    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
    XmlAccessType
    -0.64
    SBATCH
    -0.63
    osomes
    -0.58
    trums
    -0.57
    Vorlage
    -0.55
    hirts
    -0.55
    osomal
    -0.55
    :✨
    -0.53
    !*\
    -0.52
    ulink
    -0.52
    POSITIVE LOGITS
     mechanism
    0.88
     latch
    0.86
     switch
    0.86
     switches
    0.83
     mechanisms
    0.83
     Latch
    0.83
     lock
    0.81
     locking
    0.80
     interruptor
    0.79
     Mechanism
    0.77
    Activations Density 0.389%

    No Known Activations