© 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. 19-GEMMASCOPE-RES-16K
    11. 11386
    Prev
    Next
    INDEX
    Explanations

    references to hierarchy or authority structures

    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
    antMatchers
    -0.56
    AllowUser
    -0.45
     trier
    -0.41
    AutoField
    -0.35
    metery
    -0.35
     disposição
    -0.35
    avenir
    -0.35
    stuffs
    -0.35
    intellij
    -0.34
     ziua
    -0.34
    POSITIVE LOGITS
     auspices
    1.30
     umbrella
    1.22
     aegis
    1.07
     supervision
    1.02
     umbrellas
    0.99
    umbrella
    0.99
     guise
    0.91
     under
    0.90
     watchful
    0.88
     banner
    0.88
    Activations Density 0.168%

    No Known Activations