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. 12100
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly the names of individuals and companies

    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
     viata
    -0.57
     leksikon
    -0.57
     Вікіпе
    -0.54
     recevrez
    -0.53
     calitate
    -0.51
     Vikipedi
    -0.51
    клопе
    -0.49
     băr
    -0.49
     Baillargeon
    -0.48
     prieten
    -0.48
    POSITIVE LOGITS
    __*/
    0.79
    >--}}
    0.71
    insics
    0.66
    vode
    0.65
    nodoc
    0.64
    !*\
    0.62
    WEBPACK
    0.60
    )))));
    0.58
    رشف
    0.58
    IntoConstraints
    0.57
    Activations Density 0.679%

    No Known Activations