© 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. 8-GEMMASCOPE-RES-16K
    11. 9201
    Prev
    Next
    INDEX
    Explanations

    occurrences of function call syntax, particularly those involving parentheses and various types of string literals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.87
     E
    -0.85
     G
    -0.84
     L
    -0.76
     P
    -0.75
     U
    -0.75
     W
    -0.75
     l
    -0.74
     to
    -0.73
     u
    -0.72
    POSITIVE LOGITS
     للمعارف
    1.40
     myſelf
    1.28
     Majefty
    1.20
     greateſt
    1.17
     __('
    1.16
    ſelves
    1.13
    ^(@)
    1.12
     moschino
    1.12
    ](#
    1.12
     Monfieur
    1.11
    Activations Density 0.137%

    No Known Activations