Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8139
    Prev
    Next
    INDEX
    Explanations

    references to potatoes, with an emphasis on their preparation, dishes, and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.63
    Datuak
    -0.58
    prisma
    -0.56
    Solubility
    -0.55
    ="#"><
    -0.54
    といけない
    -0.54
    codiles
    -0.53
    nictwa
    -0.52
     bowls
    -0.51
    nastics
    -0.50
    POSITIVE LOGITS
     Potato
    0.98
    Potato
    0.87
     potato
    0.87
     kasarigan
    0.77
     Kartoff
    0.72
    potato
    0.70
     Hats
    0.61
    出版年
    0.59
    ✭✭
    0.58
    borderFill
    0.56
    Activations Density 0.121%

    No Known Activations