© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1060
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to HTML document structure

    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
    bootstrapcdn
    -0.67
    ://
    -0.46
    텍
    -0.46
    .
    -0.46
     Mar
    -0.45
    )
    -0.44
     M
    -0.43
    Hag
    -0.43
     X
    -0.43
     Hag
    -0.43
    POSITIVE LOGITS
     itſelf
    1.06
     myſelf
    1.00
     raiſ
    0.92
     ſeveral
    0.91
     pleaſure
    0.88
     themſelves
    0.88
     Pingback
    0.87
     Monfieur
    0.87
     fufficient
    0.86
     leſs
    0.85
    Activations Density 0.101%

    No Known Activations