© 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. 3-GEMMASCOPE-RES-16K
    11. 10433
    Prev
    Next
    INDEX
    Explanations

    HTML structure and layout elements, particularly focusing on rows and columns in a grid system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ----</
    -0.71
    достатки
    -0.66
     correctes
    -0.63
     purpoſe
    -0.61
    InvalidProtocol
    -0.61
    Jeografia
    -0.59
     تانيه
    -0.58
     PLWABN
    -0.57
     Pyrr
    -0.57
     Houſe
    -0.56
    POSITIVE LOGITS
    Row
    1.03
    row
    0.99
     row
    0.97
     Row
    0.96
    ParallelGroup
    0.85
    ROW
    0.69
    ISupport
    0.68
    ItemGroup
    0.66
    addCriterion
    0.62
    setHorizontal
    0.62
    Activations Density 0.016%

    No Known Activations