© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 15710
    Prev
    Next
    INDEX
    Explanations

    questions and conditions related to validation and approval processes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "[word] or [word]" structure

    np_acts-logits-general · gemini-2.0-flash

    logical OR operator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    hasia
    -0.51
    ORAL
    -0.47
     تضيفلها
    -0.44
     numberWith
    -0.44
    ご了承ください
    -0.43
    uawei
    -0.43
    moveToNext
    -0.43
    transQ
    -0.42
    ="<?=
    -0.42
    
    -0.41
    POSITIVE LOGITS
     or
    3.27
     или
    2.42
    หรือ
    2.16
     hoặc
    2.16
     atau
    2.13
    或
    2.11
     یا
    2.03
     alebo
    2.00
    或者
    1.90
     eller
    1.89
    Activations Density 9.002%

    No Known Activations