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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 3637
    Prev
    Next
    INDEX
    Explanations

    references to dietary supplements and related terms

    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
     Wayback
    -0.73
    compli
    -0.67
    RenderAtEndOf
    -0.62
    Odon
    -0.60
     erec
    -0.58
    RegressionTest
    -0.55
    Compli
    -0.54
    нъ
    -0.53
    ImageContext
    -0.53
     Rango
    -0.53
    POSITIVE LOGITS
     supplement
    1.46
     Supplement
    1.30
    supplement
    1.29
     supplements
    1.17
    Supplement
    1.14
     supplementing
    1.07
     partly
    1.01
     SUPPLEMENT
    1.00
     supplementation
    1.00
     supplemented
    1.00
    Activations Density 0.070%

    No Known Activations