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. 22-GEMMASCOPE-RES-16K
    6. 13848
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes after periods, asterisks, or the word "and"

    np_acts-logits-general · gemini-2.0-flash

    regulation, gene expression, angiogenesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Diwedd
    -0.65
     nahilalakip
    -0.63
     Wikimedijinoj
    -0.61
    GEBURTS
    -0.60
     الرخصة
    -0.59
     rhestr
    -0.58
     AssemblyVersion
    -0.56
     visst
    -0.55
     AssemblyCulture
    -0.55
     onPostExecute
    -0.54
    POSITIVE LOGITS
     Date
    0.67
    CodedInputStream
    0.64
    Date
    0.58
    makeText
    0.53
     оригіналу
    0.52
     Buy
    0.50
    iocene
    0.50
     please
    0.50
     date
    0.47
     IconData
    0.47
    Activations Density 0.065%

    No Known Activations