© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7938
    Prev
    Next
    INDEX
    Explanations

    instances of formatting or special characters in a structured text context

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

    Text before end-of-turn tokens

    np_acts-logits-general · gemini-2.0-flash

    mathematical or technical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.91
     betweenstory
    -0.72
    WEBPACK
    -0.70
     XHTML
    -0.68
    Tikang
    -0.68
    ┹
    -0.66
    Zeneca
    -0.66
    嵎
    -0.66
     zwiſchen
    -0.65
    Tembelea
    -0.65
    POSITIVE LOGITS
     purpoſe
    0.36
    .
    0.35
    !
    0.30
    antaranya
    0.29
    ！
    0.29
     skjø
    0.28
    AntiForgeryToken
    0.28
     avoient
    0.26
     auroit
    0.26
     necesite
    0.26
    Activations Density 0.111%

    No Known Activations