© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 15719
    Prev
    Next
    INDEX
    Explanations

    expressions related to miracles and extraordinary occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    衛門
    -0.48
     social
    -0.45
     situasi
    -0.45
     Social
    -0.44
     Class
    -0.43
    isset
    -0.43
     class
    -0.43
     Bentham
    -0.42
    汀
    -0.41
    Christophe
    -0.41
    POSITIVE LOGITS
     miracle
    1.69
     miracles
    1.68
    miracle
    1.55
     miraculous
    1.52
     marvels
    1.47
     wonders
    1.47
    wonder
    1.46
     wonder
    1.44
     Miracle
    1.41
     Miracles
    1.40
    Activations Density 0.337%

    No Known Activations