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. 16-GEMMASCOPE-RES-16K
    6. 6324
    Prev
    Next
    INDEX
    Explanations

    comparative phrases related to frequency, quantity, or intensity

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

    Multiples like "twice" and "times"

    np_acts-logits-general · gemini-2.0-flash

    comparisons of quantity by multiples

    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
    cektir
    -0.65
    بوابة
    -0.59
    Portale
    -0.56
    ☸
    -0.56
    flake
    -0.53
    lucent
    -0.53
     Remington
    -0.51
    ONG
    -0.51
    vertible
    -0.51
    soft
    -0.51
    POSITIVE LOGITS
    FieldBuilder
    0.68
     للمعارف
    0.67
    pazität
    0.64
    AsUp
    0.58
     iprot
    0.57
    bình
    0.56
     cromado
    0.56
    oredCriteria
    0.55
    Twice
    0.55
     lipat
    0.54
    Activations Density 0.143%

    No Known Activations