© 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. 4372
    Prev
    Next
    INDEX
    Explanations

    measurements of chemical concentrations

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

    Values with the unit "μg/mL"

    np_acts-logits-general · gemini-2.0-flash

    micrograms per milliliter

    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
    ]]
    -0.52
    newswire
    -0.50
    برد
    -0.48
     verw
    -0.48
    \{\\
    -0.47
    واب
    -0.46
    ']]
    -0.46
    헌
    -0.46
    ellants
    -0.46
    izze
    -0.45
    POSITIVE LOGITS
     Paglinawan
    0.71
    AntiForgeryToken
    0.63
     HasFactory
    0.62
    per
    0.61
    GraphicsUnit
    0.57
     per
    0.56
    bootstrapcdn
    0.56
    awtextra
    0.56
     Vikipedi
    0.55
    setopt
    0.55
    Activations Density 0.229%

    No Known Activations