© 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. 147
    Prev
    Next
    INDEX
    Explanations

    references to software packages and dependencies

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

    Software package installation or version details

    np_acts-logits-general · gemini-2.0-flash

    software installation and dependencies

    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
    antas
    -0.51
    sertation
    -0.47
    เย
    -0.46
    gapan
    -0.46
    setContentView
    -0.45
     asht
    -0.44
     Wikimedijinoj
    -0.43
    Hentet
    -0.43
    InjectAttribute
    -0.43
    աշ
    -0.42
    POSITIVE LOGITS
     package
    0.72
    \{\\
    0.70
     Package
    0.69
     distribution
    0.69
     distribuzione
    0.66
     distributions
    0.63
     dependency
    0.63
     packageName
    0.62
     Distribution
    0.62
    ंदीखरीदारी
    0.62
    Activations Density 0.551%

    No Known Activations