Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3346
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or section

    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
    AccessorTable
    -0.93
     שוליים
    -0.80
    WillAppear
    -0.75
     kasarigan
    -0.74
    
    -0.73
    новниш
    -0.72
    ViewFeatures
    -0.69
    AlterField
    -0.68
     Fati
    -0.67
    StructEnd
    -0.67
    POSITIVE LOGITS
     agra
    0.52
    ècie
    0.48
     dél
    0.48
     bucal
    0.47
    外部リンク
    0.46
     Türkei
    0.44
    hadap
    0.43
     nhật
    0.42
     grail
    0.42
     المرجع
    0.42
    Activations Density 0.673%

    No Known Activations