© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 15743
    Prev
    Next
    INDEX
    Explanations

    terms related to component sizes in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pouvoit
    -0.73
    MigrationBuilder
    -0.70
     Theſe
    -0.66
     écou
    -0.65
     étoit
    -0.63
     feroit
    -0.63
     recevez
    -0.62
     auroit
    -0.62
     photolibrary
    -0.61
    Попис
    -0.61
    POSITIVE LOGITS
    Size
    1.94
     Size
    1.65
     size
    1.32
     SIZE
    1.20
    SIZE
    1.19
    size
    1.17
     Größe
    0.91
     Sizes
    0.91
     sizes
    0.86
    サイズ
    0.80
    Activations Density 0.021%

    No Known Activations