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. 19-GEMMASCOPE-RES-16K
    6. 11340
    Prev
    Next
    INDEX
    Explanations

    phrases that describe the structure and composition of systems or devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.83
    出版年
    -0.75
    saraba
    -0.66
    tangentMode
    -0.65
     Biôgrafia
    -0.63
    executeUpdate
    -0.62
     chuyện
    -0.57
    IVEREF
    -0.57
     Савезне
    -0.56
     referrerpolicy
    -0.55
    POSITIVE LOGITS
     consisting
    2.64
     consists
    2.63
     consisted
    2.39
     composed
    2.38
     consist
    2.37
     comprised
    2.37
     comprising
    2.14
     terdiri
    2.09
     comprises
    2.08
     Composed
    2.00
    Activations Density 0.810%

    No Known Activations