© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 127263
    Prev
    Next
    INDEX
    Explanations

    references to foreign objects and their interactions with the environment

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

    foreign bodies and debris

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     berdasarkan
    -0.33
    ESTAMP
    -0.31
     Gier
    -0.31
    butuhkan
    -0.30
     Arco
    -0.30
    ampilan
    -0.29
     voors
    -0.29
     پیشن
    -0.29
     schlä
    -0.29
    ẻo
    -0.29
    POSITIVE LOGITS
    ########.
    0.74
     debris
    0.69
    adaptiveStyles
    0.69
     EconPapers
    0.66
     snippetHide
    0.65
     שוליים
    0.59
     kasarigan
    0.59
     Debris
    0.59
     stone
    0.58
    ReusableCell
    0.57
    Activations Density 0.138%

    No Known Activations