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. 6199
    Prev
    Next
    INDEX
    Explanations

    narratives involving aggressive confrontations and violent interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     FetchType
    -0.69
     виправивши
    -0.68
     diurnal
    -0.64
     günlük
    -0.63
     Roskov
    -0.60
     quotidien
    -0.58
     kasarigan
    -0.56
    noons
    -0.56
     morrow
    -0.56
     daily
    -0.55
    POSITIVE LOGITS
     initially
    0.67
     sempat
    0.63
     shouted
    0.54
     reportedly
    0.53
     Initially
    0.53
     briefly
    0.52
     then
    0.51
     dichter
    0.51
     yelled
    0.51
     następnie
    0.50
    Activations Density 0.336%

    No Known Activations