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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 7709
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and variable definitions within a technical context

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

    "Eleventh" or variables with subscript 11

    np_acts-logits-general · gemini-2.0-flash

    numbers and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tenth
    -0.59
     zeros
    -0.58
     ten
    -0.58
     zeroes
    -0.56
     Ten
    -0.56
    Ten
    -0.55
    Parcelize
    -0.54
     tenth
    -0.53
    DataAnnotations
    -0.53
     kuchni
    -0.53
    POSITIVE LOGITS
    enumii
    0.69
    पया
    0.59
     Eleventh
    0.57
    VersionUID
    0.57
    styleable
    0.51
     eleventh
    0.51
    regalo
    0.51
    parsedMessage
    0.51
    IntoConstraints
    0.49
    blage
    0.48
    Activations Density 0.366%

    No Known Activations