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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13442
    Prev
    Next
    INDEX
    Explanations

    terms related to successful actions or outcomes

    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
    見た
    -0.68
     adjustment
    -0.58
     manche
    -0.57
    roffen
    -0.57
     UnityEngine
    -0.56
     reten
    -0.56
    sud
    -0.53
     ná
    -0.53
     healed
    -0.52
    lap
    -0.51
    POSITIVE LOGITS
     safely
    1.69
     successfully
    1.63
    successfully
    1.55
     quietly
    1.49
     silently
    1.49
     actively
    1.44
     peacefully
    1.43
     confidently
    1.43
     Successfully
    1.41
     Safely
    1.39
    Activations Density 0.204%

    No Known Activations