© 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. 10-GEMMASCOPE-RES-16K
    6. 11365
    Prev
    Next
    INDEX
    Explanations

    significant personal achievements or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.69
     cherchés
    -0.66
    findpost
    -0.65
    Портал
    -0.63
    
    -0.59
    bitField
    -0.59
     IActionResult
    -0.56
    RectangleBorder
    -0.56
     ***!
    -0.55
    الحياه
    -0.54
    POSITIVE LOGITS
    principalTable
    0.58
     resourceCulture
    0.51
    PreferredItem
    0.51
     blessés
    0.49
     prêtres
    0.49
     téléph
    0.49
    LLocation
    0.49
     McCull
    0.48
    IUrlHelper
    0.46
     rempliss
    0.46
    Activations Density 0.697%

    No Known Activations