© 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. 5-GEMMASCOPE-RES-16K
    11. 9122
    Prev
    Next
    INDEX
    Explanations

    function calls or method names related to data subscription and entity properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     even
    -0.52
     face
    -0.51
     https
    -0.50
    okkal
    -0.50
    OUS
    -0.49
    ace
    -0.49
     FACE
    -0.49
    bes
    -0.49
    face
    -0.49
     antar
    -0.48
    POSITIVE LOGITS
    :✨
    2.16
    DoubleQuotes
    1.79
    PathVariable
    1.63
     ProtoMessage
    1.41
    EndInit
    1.41
    IsMutable
    1.33
    UnsafeEnabled
    1.32
    BeginInit
    1.29
    elemField
    1.28
    webElementXpaths
    1.23
    Activations Density 0.010%

    No Known Activations