© 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. 9-GEMMASCOPE-RES-16K
    11. 8878
    Prev
    Next
    INDEX
    Explanations

    phrases indicating inclusivity or the concept of "all" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     algunas
    -0.61
     not
    -0.61
     algunos
    -0.59
     two
    -0.56
     more
    -0.54
    bouncycastle
    -0.54
     algumas
    -0.53
     Not
    -0.53
     certain
    -0.52
     Two
    -0.52
    POSITIVE LOGITS
    everything
    1.07
     Tutte
    1.02
     everything
    1.00
     Everything
    0.99
     EVERYTHING
    0.99
     đều
    0.99
    Everything
    0.98
     imaginable
    0.98
    Semua
    0.97
    Tudo
    0.96
    Activations Density 0.801%

    No Known Activations