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. 12098
    Prev
    Next
    INDEX
    Explanations

    specific numerical data or references related to events or entities

    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
    StoreMessageInfo
    -0.66
    sizeCache
    -0.64
    #+#
    -0.60
    tangentMode
    -0.60
     indisponible
    -0.55
    tvguidetime
    -0.55
    kuuta
    -0.54
     الفلك
    -0.54
    portál
    -0.53
    CPC
    -0.53
    POSITIVE LOGITS
    5
    0.61
    9
    0.60
    6
    0.58
    8
    0.56
    4
    0.56
    7
    0.56
    3
    0.54
     Ramadan
    0.54
     '{@
    0.53
     Holi
    0.53
    Activations Density 0.115%

    No Known Activations