© 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. 25-GEMMASCOPE-RES-16K
    11. 3245
    Prev
    Next
    INDEX
    Explanations

    references to categories or types of items, particularly numerical representations or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hutchison
    -0.68
     Crouch
    -0.68
     Fletcher
    -0.67
     Hough
    -0.67
     Lillie
    -0.67
     Scorpion
    -0.63
     Igles
    -0.62
     Malhotra
    -0.62
     AssemblyCulture
    -0.61
     McDonough
    -0.61
    POSITIVE LOGITS
     Rodriguez
    0.73
    phi
    0.70
     Baha
    0.69
     Chaco
    0.69
    Crist
    0.67
     Lande
    0.67
     Kopp
    0.67
     Crist
    0.66
     phi
    0.65
     Garcia
    0.64
    Activations Density 1.510%

    No Known Activations