© 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. 10-GEMMASCOPE-RES-16K
    6. 13023
    Prev
    Next
    INDEX
    Explanations

    mentions of historical events and their socioeconomic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebElementEntity
    -0.69
     &___
    -0.61
    CodeAnalysis
    -0.53
    GMENT
    -0.51
    佗
    -0.49
    InSection
    -0.49
     propOrder
    -0.48
    íba
    -0.48
    SupportActionBar
    -0.48
    VisualStudio
    -0.47
    POSITIVE LOGITS
     hinweg
    0.77
     समीक्षक
    0.68
    Viitteet
    0.56
    InvalidProtocol
    0.52
    awm
    0.52
     gynhyrchwyd
    0.51
     désolés
    0.51
    üyada
    0.50
     Biôgrafia
    0.50
     Malt
    0.50
    Activations Density 0.441%

    No Known Activations