© 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. 18-GEMMASCOPE-RES-16K
    11. 9037
    Prev
    Next
    INDEX
    Explanations

    elements related to definitions or descriptions of technical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences following introductory phrases

    np_acts-logits-general · gemini-2.0-flash

    . followed by capitalised word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dlatego
    -0.64
     hence
    -0.61
    Hence
    -0.60
    latego
    -0.60
    WithIOException
    -0.60
    PerformLayout
    -0.60
     跳转至
    -0.59
     therefore
    -0.58
    EndInit
    -0.58
    SizeMode
    -0.56
    POSITIVE LOGITS
    所谓
    0.79
     Basically
    0.75
    basically
    0.72
    Basically
    0.72
     суть
    0.69
     basically
    0.68
    该
    0.67
    Essentially
    0.66
     Essentially
    0.66
     该
    0.64
    Activations Density 0.344%

    No Known Activations