© 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. 7639
    Prev
    Next
    INDEX
    Explanations

    phrases related to privacy and personal information

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

    in languages other than English

    np_acts-logits-general · gemini-2.0-flash

    code in call

    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
     Vordergrund
    -0.57
     eigenes
    -0.56
     solches
    -0.50
     Gedanke
    -0.50
    上的
    -0.49
     Leute
    -0.49
    下的
    -0.49
     anderes
    -0.48
    方面的
    -0.48
     Wortes
    -0.48
    POSITIVE LOGITS
    хьтан
    0.62
     चीज़ों
    0.58
    文件中
    0.57
    游戏中
    0.54
     насељу
    0.54
    jspb
    0.53
    awtextra
    0.51
    일에
    0.51
    einem
    0.50
     einem
    0.50
    Activations Density 0.022%

    No Known Activations