© 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. 2-GEMMASCOPE-RES-16K
    11. 467
    Prev
    Next
    INDEX
    Explanations

    references to data integrity or security in the context of web resources

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    findpost
    -0.52
     yea
    -0.47
     rayas
    -0.45
    __(/*!
    -0.45
    PreferredItem
    -0.45
    ariales
    -0.45
     pierna
    -0.45
    ChildScrollView
    -0.44
     camiset
    -0.44
    enumii
    -0.43
    POSITIVE LOGITS
    Y
    2.59
     Y
    1.83
    Ｙ
    1.19
    𝐘
    0.83
    Ys
    0.76
    YF
    0.75
    𝗬
    0.73
    YV
    0.72
    Yt
    0.71
    Yy
    0.71
    Activations Density 0.185%

    No Known Activations