© 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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 13155
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "release" in various contexts

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     getIs
    -0.54
     zelf
    -0.48
     Big
    -0.45
    kers
    -0.44
    complexContent
    -0.43
    がか
    -0.43
     holidays
    -0.42
    uens
    -0.41
    ướt
    -0.41
    aufs
    -0.41
    POSITIVE LOGITS
    release
    1.84
     release
    1.83
     Release
    1.76
    Release
    1.63
     RELEASE
    1.62
    RELEASE
    1.41
     releasing
    1.30
     Released
    1.30
    Released
    1.27
     releases
    1.26
    Activations Density 0.083%

    No Known Activations