© 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. 10761
    Prev
    Next
    INDEX
    Explanations

    references to features in various contexts

    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
     pregunto
    -0.88
    Alp
    -0.87
     Pamph
    -0.84
     PVA
    -0.80
     photolibrary
    -0.80
     geboren
    -0.80
     pessoais
    -0.80
     meisten
    -0.78
     clearColor
    -0.77
    thschild
    -0.77
    POSITIVE LOGITS
     features
    2.95
     feature
    2.74
     Features
    2.64
    features
    2.51
    Features
    2.47
     Feature
    2.46
     FEATURE
    2.38
    Feature
    2.36
     FEATURES
    2.32
    feature
    2.31
    Activations Density 0.061%

    No Known Activations