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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 1677
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an explanation or clarification of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fer
    -0.54
     early
    -0.53
    anelas
    -0.50
     hingga
    -0.48
    own
    -0.48
     nadzieję
    -0.47
    est
    -0.46
     regular
    -0.45
    up
    -0.45
    monary
    -0.45
    POSITIVE LOGITS
    Isso
    1.43
    Это
    1.34
     Isso
    1.31
     Это
    1.29
     cela
    1.27
     ça
    1.17
     isso
    1.17
     это
    1.16
     esto
    1.13
    это
    1.11
    Activations Density 0.056%

    No Known Activations