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. 12116
    Prev
    Next
    INDEX
    Explanations

    descriptions related to bedding products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     “
    -0.63
     hitherto
    -0.58
    expensive
    -0.56
     expensive
    -0.56
     fucking
    -0.55
     cheaper
    -0.54
     FUCKING
    -0.54
     Apparently
    -0.53
    apparently
    -0.53
     caros
    -0.53
    POSITIVE LOGITS
     beginnetje
    0.74
    GEBURTSDATUM
    0.73
     youll
    0.72
    OOTDTY
    0.71
     nahilalakip
    0.70
     picioare
    0.69
     Monfieur
    0.68
    bootstrapcdn
    0.67
    PreferredItem
    0.64
     clín
    0.64
    Activations Density 0.090%

    No Known Activations