© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57995
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaiter
    -0.76
    ItemBackground
    -0.71
     universale
    -0.68
    AndroidJUnit
    -0.62
     Magellan
    -0.60
     Noten
    -0.60
     démission
    -0.60
    DIPSETTING
    -0.59
     chi̍t
    -0.58
     japonesa
    -0.57
    POSITIVE LOGITS
    Grath
    0.52
     Vla
    0.50
     Durchsch
    0.47
    atschappij
    0.47
    haviors
    0.46
    hipping
    0.46
     Мексичка
    0.46
     CURIAM
    0.46
    eddable
    0.45
    innis
    0.45
    Activations Density 0.046%

    No Known Activations