© 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. 14335
    Prev
    Next
    INDEX
    Explanations

    alphanumeric characters and their frequency in various contexts

    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
    τως
    -0.61
    bauer
    -0.49
     fas
    -0.47
     balance
    -0.47
    violi
    -0.46
     inf
    -0.45
     safety
    -0.45
     Carter
    -0.43
    ानी
    -0.43
     oral
    -0.42
    POSITIVE LOGITS
    tagHelperRunner
    0.75
    Jîn
    0.74
     Meksiku
    0.73
    webElementGuid
    0.72
    rungsseite
    0.69
    BeginContext
    0.69
    :✨
    0.68
    brainly
    0.65
    webElementXpaths
    0.65
     الرياضيه
    0.63
    Activations Density 0.123%

    No Known Activations