© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 5869
    Prev
    Next
    INDEX
    Explanations

    content related to quality and diversity in creative expressions and cultural representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Extern
    -0.59
     générales
    -0.58
    oulli
    -0.57
     Outside
    -0.54
    WebElementEntity
    -0.53
     Mechan
    -0.53
     outsiders
    -0.51
     extern
    -0.51
    ้อม
    -0.50
     الخارج
    -0.50
    POSITIVE LOGITS
     locally
    1.28
     local
    1.23
    Locally
    1.22
    locally
    1.12
     Locally
    1.11
    Local
    1.07
    local
    1.07
     Local
    0.98
     LOCAL
    0.95
     lokal
    0.93
    Activations Density 0.400%

    No Known Activations