© 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. 25-GEMMASCOPE-RES-16K
    6. 8398
    Prev
    Next
    INDEX
    Explanations

    historical origins and the evolution of concepts or entities over time

    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
    AndEndTag
    -0.67
     VIAF
    -0.64
     الحره
    -0.63
    +#+#
    -0.61
    gameserver
    -0.60
     ब्रेकडाउन
    -0.59
     AssemblyCulture
    -0.56
    liothèque
    -0.55
    Искәрмәләр
    -0.52
     Lightboxes
    -0.51
    POSITIVE LOGITS
     dating
    2.04
     dates
    1.88
    dating
    1.68
     date
    1.60
     dated
    1.56
     remonte
    1.55
     Dating
    1.55
    Dating
    1.43
     Dates
    1.43
    dates
    1.43
    Activations Density 0.522%

    No Known Activations