© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 14855
    Prev
    Next
    INDEX
    Explanations

    French pronouns and articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -1.07
     Witt
    -0.84
     οποία
    -0.77
     espress
    -0.77
    nya
    -0.75
    ness
    -0.75
    böz
    -0.72
     Ej
    -0.72
    NameInMap
    -0.72
     bezeichneter
    -0.69
    POSITIVE LOGITS
     Parke
    0.88
     στη
    0.86
     detainees
    0.84
     Bue
    0.83
    anskje
    0.82
     Thy
    0.82
     aDecoder
    0.80
     huellas
    0.78
     τη
    0.77
    ΤΗ
    0.76
    Activations Density 0.024%

    No Known Activations