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. 13-GEMMASCOPE-RES-16K
    6. 8503
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Getty" and references to 'Math'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -0.86
     PLWABN
    -0.72
     servici
    -0.68
    ukone
    -0.66
     getNombre
    -0.65
    cerely
    -0.64
    curities
    -0.63
    >\<
    -0.62
     Chwiliwch
    -0.61
     cartaz
    -0.60
    POSITIVE LOGITS
    MathML
    0.91
    usermodel
    0.90
    Math
    0.73
    migrationBuilder
    0.69
    存于互联网档案馆
    0.56
    usercontent
    0.55
     CURLOPT
    0.54
    CrossRef
    0.53
     GenerationType
    0.52
     arşivlendi
    0.52
    Activations Density 0.026%

    No Known Activations