© 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. 15261
    Prev
    Next
    INDEX
    Explanations

    instances of the word "short."

    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
     AssemblyVersion
    -0.64
     IConfiguration
    -0.63
     GetEnumerator
    -0.62
     ModelAndView
    -0.62
    ItemBackground
    -0.61
     roleId
    -0.60
    MessageTagHelper
    -0.58
    laubnis
    -0.58
    DidLoad
    -0.58
     oeil
    -0.57
    POSITIVE LOGITS
     short
    4.39
    Short
    4.28
     Short
    4.28
    short
    4.15
     SHORT
    3.92
    SHORT
    3.76
     shorter
    3.29
    短
    3.03
     shortest
    2.91
     shorten
    2.78
    Activations Density 0.085%

    No Known Activations