© 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. 3-GEMMASCOPE-RES-16K
    11. 1995
    Prev
    Next
    INDEX
    Explanations

    references to angels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.78
     disponibilités
    -0.78
     noDo
    -0.76
     Falkland
    -0.74
     Theſe
    -0.73
     SND
    -0.72
     Alois
    -0.69
     Agrico
    -0.68
     Jove
    -0.68
     Kuba
    -0.67
    POSITIVE LOGITS
     Angel
    1.92
    Angel
    1.73
     angel
    1.65
     Angels
    1.47
     ANGEL
    1.42
     angels
    1.37
    Angels
    1.32
     ángel
    1.30
    ANGEL
    1.25
    angel
    1.20
    Activations Density 0.059%

    No Known Activations