© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13490
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly authors or contributors

    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
     French
    -0.73
    French
    -0.64
     FRENCH
    -0.64
    tagHelperRunner
    -0.58
     french
    -0.56
     Parisi
    -0.56
     Frenchman
    -0.54
     frances
    -0.54
    ništvo
    -0.52
     francesa
    -0.51
    POSITIVE LOGITS
    igeon
    0.58
    +#+
    0.56
    colas
    0.55
    :+:
    0.55
    égard
    0.52
     Parent
    0.50
     Four
    0.50
     FOUR
    0.50
    ранже
    0.50
    guy
    0.49
    Activations Density 0.304%

    No Known Activations