© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1320
    Prev
    Next
    INDEX
    Explanations

    specific mentions of proposals or initiatives related to healthcare or management

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

    Follows a period or punctuation

    np_acts-logits-general · gemini-2.0-flash

    comments following replies

    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
    MENAFN
    -0.69
     cherchés
    -0.67
    tvguidetime
    -0.67
    nationality
    -0.63
     fallu
    -0.62
    MultipartFile
    -0.60
    原始内容存档于
    -0.60
    eabouts
    -0.59
     AssemblyCompany
    -0.59
    AutoScaleMode
    -0.59
    POSITIVE LOGITS
     verbal
    0.67
     response
    0.67
     politely
    0.66
     tact
    0.66
     responses
    0.66
     overheard
    0.64
     unsolicited
    0.63
     reply
    0.63
     nonverbal
    0.63
     Verbal
    0.63
    Activations Density 0.532%

    No Known Activations