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. 10-GEMMASCOPE-RES-16K
    6. 12614
    Prev
    Next
    INDEX
    Explanations

    references to self-awareness and gestures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     møte
    -0.58
     complètes
    -0.54
     vectorielles
    -0.53
     sposa
    -0.52
     mariée
    -0.51
     completos
    -0.51
     vectorielle
    -0.50
     imprimée
    -0.50
     noiva
    -0.49
     sorpresas
    -0.49
    POSITIVE LOGITS
     fidget
    0.68
    Билгалдахарш
    0.68
    HomeAsUpEnabled
    0.67
    protoimpl
    0.65
     esternos
    0.63
    Ligações
    0.63
    Personensuche
    0.61
     obses
    0.60
    idget
    0.60
     incessantly
    0.59
    Activations Density 0.385%

    No Known Activations