© 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. 6-GEMMASCOPE-RES-16K
    11. 3986
    Prev
    Next
    INDEX
    Explanations

    the presence of specific keywords and tags related to events, management, and action items

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.80
     at
    -0.54
     to
    -0.54
     utafitiHapana
    -0.53
     on
    -0.53
    '
    -0.53
     
    -0.53
     of
    -0.52
     (
    -0.50
     or
    -0.50
    POSITIVE LOGITS
    تقاوى
    0.96
    yntaxException
    0.88
    UnsafeEnabled
    0.82
    TypedDataSet
    0.81
     myſelf
    0.80
    انيف
    0.79
    Tikang
    0.78
    хьтан
    0.75
    batore
    0.74
     Wicidata
    0.74
    Activations Density 0.180%

    No Known Activations