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. 12059
    Prev
    Next
    INDEX
    Explanations

    terms indicating quantities or classifications of items

    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
    %"),
    -0.48
    itse
    -0.47
    riwal
    -0.45
    ukone
    -0.43
    googleapis
    -0.42
    EventQueue
    -0.42
    cloudfront
    -0.42
     beziehungs
    -0.41
    itz
    -0.41
    }());
    -0.40
    POSITIVE LOGITS
     delas
    1.15
     deles
    1.09
     davon
    1.00
     ones
    0.96
     daarvan
    0.83
     ervan
    0.83
     others
    0.81
     تضيفلها
    0.81
     satunya
    0.80
     nahilalakip
    0.78
    Activations Density 0.465%

    No Known Activations