© 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. 952
    Prev
    Next
    INDEX
    Explanations

    specific product names and technical specifications

    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
    
    -0.56
    Nuorodos
    -0.46
    yr
    -0.46
     Si
    -0.45
    ImageBackground
    -0.44
    ypep
    -0.43
     solas
    -0.43
     BoxDecoration
    -0.43
    ecycle
    -0.43
    ών
    -0.42
    POSITIVE LOGITS
    WebElementEntity
    0.71
    Tē
    0.58
     للاسماء
    0.58
     initComponents
    0.57
    Locality
    0.57
     meille
    0.56
     downvoted
    0.55
    ::_('
    0.55
     kaarangay
    0.55
    ContentLoaded
    0.54
    Activations Density 0.727%

    No Known Activations