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. 16-GEMMASCOPE-RES-16K
    6. 1473
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of the word "that."

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

    Text after commas, "that", or quotation marks

    np_acts-logits-general · gemini-2.0-flash

    that followed by this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SOUNDBITE
    -0.75
    cellaneous
    -0.61
    -------------</
    -0.59
    genheim
    -0.57
    iteiten
    -0.57
    ườ
    -0.56
    heça
    -0.56
    ../
    -0.56
    ksessa
    -0.55
    ensa
    -0.55
    POSITIVE LOGITS
    BeginContext
    0.73
    Tembelea
    0.70
     this
    0.67
     >=",
    0.66
     makeStyles
    0.64
     there
    0.59
    GraphicsUnit
    0.55
     although
    0.55
     these
    0.55
    this
    0.53
    Activations Density 0.276%

    No Known Activations