© 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. 185
    Prev
    Next
    INDEX
    Explanations

    terms indicating comparative benefits or advantages in a scientific or technical context

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

    ending in "ously", "ous", or "ogene"

    np_acts-logits-general · gemini-2.0-flash

    words ending in ously

    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
    endphp
    -0.90
     Bioaccumulative
    -0.80
    原始内容存档于
    -0.74
    Datuak
    -0.74
    脚注の使い方
    -0.72
    énieurs
    -0.70
     Splitter
    -0.69
    IsMutable
    -0.68
    PerformLayout
    -0.65
     виправивши
    -0.64
    POSITIVE LOGITS
    ously
    1.52
    ous
    1.42
    OUS
    1.17
    IOUS
    1.02
    ious
    0.89
    iously
    0.86
    uous
    0.84
    rous
    0.83
    ousand
    0.82
    ouss
    0.82
    Activations Density 0.250%

    No Known Activations