© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2358
    Prev
    Next
    INDEX
    Explanations

    references to statistics or proportions expressed as percentages

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    jekk
    -0.59
    stle
    -0.50
    AlterField
    -0.50
     <-
    -0.50
    LError
    -0.49
    LayoutParams
    -0.49
    PDIR
    -0.47
    帖最后由
    -0.47
    rzost
    -0.47
    minlength
    -0.47
    POSITIVE LOGITS
     percentage
    2.49
     percent
    2.24
    percentage
    2.20
     percentages
    2.17
     Percentage
    2.16
    percent
    2.15
     PERCENT
    2.13
     Percent
    2.12
    Percent
    2.08
    Percentage
    2.08
    Activations Density 0.187%

    No Known Activations