© 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. 0-GEMMASCOPE-RES-16K
    11. 16011
    Prev
    Next
    INDEX
    Explanations

    instances of the word "with" in various contexts, suggesting an emphasis on collaborative or combinatory actions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    DockStyle
    -1.38
     ModelExpression
    -1.00
    +#+#
    -0.96
     MessageBoxIcon
    -0.95
    AnchorStyles
    -0.94
     CreateTagHelper
    -0.92
     Wiktionnaire
    -0.88
    bootstrapcdn
    -0.87
    AntiForgeryToken
    -0.85
    \{\\
    -0.84
    POSITIVE LOGITS
    with
    1.14
    WITH
    1.09
    With
    0.80
     With
    0.71
     WITH
    0.67
    dengan
    0.66
     with
    0.66
    Билгалдахарш
    0.60
    without
    0.59
     fédé
    0.58
    Activations Density 0.197%

    No Known Activations