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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12340
    Prev
    Next
    INDEX
    Explanations

    keywords related to various sectors of business and industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    französ
    -0.58
     تعدى
    -0.57
    GEBURTSDATUM
    -0.55
     noDo
    -0.55
     situe
    -0.51
    SessionFactory
    -0.49
     rather
    -0.48
    hoeddwyd
    -0.48
     tempore
    -0.47
     @"/
    -0.47
    POSITIVE LOGITS
     etc
    1.37
     usw
    1.19
    etc
    1.12
     itp
    1.01
    などなど
    1.01
     Etc
    0.95
    Etc
    0.91
    等等
    0.86
     וכו
    0.86
     stb
    0.83
    Activations Density 1.213%

    No Known Activations