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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 710
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs, particularly related to function definitions and service calls

    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
    +#+#
    -0.73
     onCancelled
    -0.66
     enfans
    -0.58
     venons
    -0.57
     Shakspeare
    -0.56
     décid
    -0.56
     Majefty
    -0.56
     legale
    -0.54
     sentenza
    -0.53
     auroit
    -0.53
    POSITIVE LOGITS
     save
    0.55
     insert
    0.55
     select
    0.51
     find
    0.49
     delete
    0.48
    VersionUID
    0.47
     change
    0.47
     Insert
    0.47
     bait
    0.46
    FontOfSize
    0.45
    Activations Density 0.046%

    No Known Activations