Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 1021
    Prev
    Next
    INDEX
    Explanations

    terms related to "pen" including its variations and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -1.00
    parsedMessage
    -0.77
    EDEFAULT
    -0.75
    Tikang
    -0.71
    }{*}{}
    -0.71
     مشين
    -0.70
    DeleteBehavior
    -0.69
    webElementXpaths
    -0.66
     nahilalakip
    -0.62
    TypedDataSet
    -0.62
    POSITIVE LOGITS
     pen
    0.72
    pen
    0.58
     Pen
    0.56
     PEN
    0.54
     Penit
    0.52
    Pen
    0.51
    Pens
    0.50
     Arkivert
    0.50
     pens
    0.49
     Pennington
    0.49
    Activations Density 0.251%

    No Known Activations