© 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 - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 12823
    Prev
    Next
    INDEX
    Explanations

    symbols or formats typically used in mathematical or technical notation

    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
     المعيارى
    -0.96
     وتسجيلات
    -0.84
     jScrollPane
    -0.71
     незавершена
    -0.67
    Чыганаклар
    -0.66
    PyExc
    -0.65
     Ressources
    -0.65
    adaptiveStyles
    -0.65
    Демографія
    -0.64
     Савезне
    -0.63
    POSITIVE LOGITS
    *
    0.62
     كمان
    0.61
    checksum
    0.52
     skär
    0.52
     limitée
    0.51
     península
    0.51
     cantit
    0.50
     getattr
    0.50
     culoare
    0.49
     ää
    0.49
    Activations Density 0.220%

    No Known Activations