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. 22-GEMMASCOPE-RES-16K
    6. 8661
    Prev
    Next
    INDEX
    Explanations

    references to products and descriptions of features or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Descriptions of features/capabilities

    np_acts-logits-general · gemini-2.0-flash

    features or capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.56
     برانيه
    -0.54
    QtWidgets
    -0.53
    internalType
    -0.50
     Affects
    -0.49
    GIVEREF
    -0.49
     gọi
    -0.48
    EnableWeb
    -0.48
    forKey
    -0.47
    HasForeignKey
    -0.47
    POSITIVE LOGITS
     boast
    1.12
     boasts
    1.11
     features
    1.09
     offers
    1.03
     feature
    0.94
     offer
    0.90
    features
    0.89
    offers
    0.88
     boasting
    0.87
     Features
    0.87
    Activations Density 0.201%

    No Known Activations