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. 3180
    Prev
    Next
    INDEX
    Explanations

    the beginning and structure of textual content

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

    Follows initiating words such as "This," "Of," or numbers

    np_acts-logits-general · gemini-2.0-flash

    specimens, tongue, numbers, diagnosis

    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
     كومونز
    -0.78
    InjectAttribute
    -0.70
     CreateTagHelper
    -0.65
    makeConstraints
    -0.65
     typelib
    -0.63
     Biôgrafia
    -0.61
     defaultstate
    -0.59
     scuole
    -0.59
     nakalista
    -0.59
    antMatchers
    -0.59
    POSITIVE LOGITS
    artige
    0.63
    كذا
    0.57
    lungen
    0.55
    XmlType
    0.53
    Географиясе
    0.53
    Espèce
    0.52
     Terima
    0.51
    Denne
    0.51
     GLFW
    0.50
    ceto
    0.49
    Activations Density 0.263%

    No Known Activations