© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 14019
    Prev
    Next
    INDEX
    Explanations

    instances of items being enclosed, contained, or well-stocked

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Filled" or "Rife" followed by "with"

    np_acts-logits-general · gemini-2.0-flash

    filled with or describing fullness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.48
     Dage
    -0.41
    hebt
    -0.40
    Numerade
    -0.38
    MathML
    -0.38
    IndentedString
    -0.33
    CodeDom
    -0.33
     deltaTime
    -0.32
     externs
    -0.32
    SPJ
    -0.32
    POSITIVE LOGITS
     filled
    2.03
     Filled
    1.84
    Filled
    1.65
    filled
    1.58
     rempli
    1.38
     loaded
    1.36
     fill
    1.33
     lleno
    1.29
     llena
    1.29
     filling
    1.26
    Activations Density 0.361%

    No Known Activations