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. 6-GEMMASCOPE-RES-16K
    6. 6160
    Prev
    Next
    INDEX
    Explanations

    underscores and various formatting markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.74
    CharField
    -0.68
     Deere
    -0.62
     NSCoder
    -0.62
    ltä
    -0.61
    Coucou
    -0.60
    RetentionPolicy
    -0.59
    σιμοποι
    -0.59
     métiers
    -0.58
    manjaro
    -0.58
    POSITIVE LOGITS
    WriteTagHelper
    1.06
     оригіналу
    0.80
     utafitiHapana
    0.68
    wijs
    0.67
    dialogs
    0.63
    thyst
    0.63
    äsident
    0.62
    ="_
    0.62
     تضيفلها
    0.61
    )}_
    0.61
    Activations Density 0.044%

    No Known Activations