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. 3140
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions involving variables and constants

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

    Mathematical expressions with exponents/arithmetic

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions with exponents

    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
     Biôgrafia
    -0.86
    XmlAccessType
    -0.76
     Italijani
    -0.70
    CPtr
    -0.69
     OFDb
    -0.68
    Portale
    -0.66
    #+#
    -0.64
     كومونز
    -0.60
    AndEndTag
    -0.59
    hasMoreElements
    -0.58
    POSITIVE LOGITS
     avulla
    0.49
     kaupung
    0.45
    centralwidget
    0.45
    eraard
    0.44
     vielä
    0.43
    INDA
    0.43
    ERG
    0.43
     kysy
    0.42
    ContentLoaded
    0.42
     Database
    0.41
    Activations Density 0.197%

    No Known Activations