© 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. 9826
    Prev
    Next
    INDEX
    Explanations

    keywords and functions related to programming and logging in code

    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
     myſelf
    -1.00
     raiſ
    -0.89
     uſed
    -0.88
     pleaſure
    -0.87
     ſever
    -0.85
     fevere
    -0.83
     houſe
    -0.83
     Monfieur
    -0.80
     uſe
    -0.78
     viſ
    -0.77
    POSITIVE LOGITS
    CJK
    3.91
     CJK
    0.76
    oneofs
    0.54
    aarrggbb
    0.53
     Barrios
    0.48
    ()],
    0.48
    parable
    0.48
    addImage
    0.48
    Legit
    0.46
     Daniels
    0.46
    Activations Density 0.013%

    No Known Activations