© 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. 6391
    Prev
    Next
    INDEX
    Explanations

    terminology related to healthcare and medical assessments

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

    Followed by punctuation or capitalization

    np_acts-logits-general · gemini-2.0-flash

    law of the case

    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
    ,
    -1.10
     
    -1.10
     in
    -0.95
    .
    -0.95
     and
    -0.92
     for
    -0.92
    -
    -0.84
     (
    -0.83
     by
    -0.82
     to
    -0.81
    POSITIVE LOGITS
     незавершена
    1.93
    Personensuche
    1.92
     CreateTagHelper
    1.89
    GEBURTSDATUM
    1.71
     تضيفلها
    1.71
    تقاوى
    1.69
    abestanden
    1.69
     Roskov
    1.68
    OGND
    1.66
     Савезне
    1.65
    Activations Density 0.248%

    No Known Activations