© 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. 8013
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to wrapping, binding, or securing items

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

    the word "wrap" or "wrapped"

    np_acts-logits-general · gemini-2.0-flash

    wrapping or being wrapped

    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
    __(/*!
    -0.43
    RTSN
    -0.43
    atrician
    -0.40
    ierzch
    -0.38
    Viitteet
    -0.37
    aarrggbb
    -0.37
    enance
    -0.36
     gorra
    -0.36
    Sunny
    -0.35
     betweenstory
    -0.35
    POSITIVE LOGITS
     wrap
    1.25
     wrapping
    1.16
     wraps
    1.15
     Wrap
    1.14
     wrapped
    1.13
     Wrapping
    1.02
    wrap
    1.02
    Wrap
    0.97
     Wraps
    0.96
     Wrapped
    0.95
    Activations Density 0.296%

    No Known Activations