© 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. 6-GEMMASCOPE-RES-16K
    6. 4937
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -1.04
     Barbier
    -0.79
    IsContent
    -0.73
    الحياه
    -0.70
    Välislingid
    -0.66
     незавершена
    -0.66
     שוליים
    -0.65
    躇
    -0.64
    مصادر
    -0.63
     الرياضيه
    -0.62
    POSITIVE LOGITS
     avoient
    0.63
     Calvert
    0.62
     puissent
    0.62
    новниш
    0.61
     aient
    0.59
     blessés
    0.59
     guerres
    0.58
    Tcl
    0.58
     acheteurs
    0.57
     Prato
    0.57
    Activations Density 0.349%

    No Known Activations