© 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. 4977
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting typical in coding or markup languages

    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
    ⓧ
    -0.63
    AutoField
    -0.62
    ksikon
    -0.62
     Exactos
    -0.59
    CloseOperation
    -0.57
     defaultstate
    -0.54
    IVEREF
    -0.53
    )$_
    -0.53
    GOTREF
    -0.52
    Bek
    -0.50
    POSITIVE LOGITS
    áni
    0.46
     uska
    0.45
    wieś
    0.45
     dié
    0.43
    createTextNode
    0.43
    OGND
    0.43
     Arxivat
    0.40
    toHaveBeenCalled
    0.39
    edero
    0.38
     muzik
    0.38
    Activations Density 0.204%

    No Known Activations