© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 7032
    Prev
    Next
    INDEX
    Explanations

    references to ores or minerals related to materials in scientific contexts

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

    ending in "re" or "tre"

    np_acts-logits-general · gemini-2.0-flash

    Tre, Ore, Ere, Ure beginnings

    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
     jScrollPane
    -0.76
    rigation
    -0.73
    initComponents
    -0.65
    脚注の使い方
    -0.62
    spesies
    -0.60
    enderror
    -0.58
     MatDialog
    -0.57
    yethylene
    -0.57
    Affirmed
    -0.56
    rician
    -0.55
    POSITIVE LOGITS
    Ere
    0.75
     Ore
    0.73
    ORE
    0.67
     CRE
    0.65
     ORE
    0.65
     Ere
    0.65
     Tyre
    0.64
    CRE
    0.63
     Ure
    0.63
    kre
    0.61
    Activations Density 0.254%

    No Known Activations