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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15667
    Prev
    Next
    INDEX
    Explanations

    keywords related to potato preparation and recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Potato viruses and degeneration

    np_acts-logits-general · gemini-2.0-flash

    potato degeneration due to tubers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     mergeFrom
    -0.69
    FilterChain
    -0.59
    
    -0.58
    wydd
    -0.57
     frame
    -0.57
     Henson
    -0.56
    ffilm
    -0.55
    wahati
    -0.54
    Билгалдахарш
    -0.54
     Frames
    -0.53
    POSITIVE LOGITS
     potato
    1.18
     potatoes
    1.16
     tubers
    1.14
     Potato
    1.08
     Potatoes
    1.06
     tuber
    1.00
    potato
    0.98
    Potato
    0.98
    Potatoes
    0.92
     Idaho
    0.89
    Activations Density 0.194%

    No Known Activations