© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8690
    Prev
    Next
    INDEX
    Explanations

    terms related to dryness, particularly in various contexts such as eyes, materials, and environments

    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
    BeginContext
    -0.76
    thâu
    -0.75
    مصادر
    -0.69
    RectangleBorder
    -0.67
    ViewImports
    -0.66
    المراجع
    -0.65
    */].
    -0.65
    ArgumentParser
    -0.65
     antaranya
    -0.64
    مراجع
    -0.62
    POSITIVE LOGITS
     dry
    3.95
     Dry
    3.67
    Dry
    3.54
    dry
    3.47
     DRY
    3.29
    DRY
    2.96
     dries
    2.67
     dryness
    2.46
     trock
    2.43
     dried
    2.40
    Activations Density 0.046%

    No Known Activations