© 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. 726
    Prev
    Next
    INDEX
    Explanations

    elements related to identities, names, or roles of individuals, including both proper nouns and descriptors

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

    Japanese and Italian text fragments

    np_acts-logits-general · gemini-2.0-flash

    小宮山君

    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
     שני
    -0.52
    ########.
    -0.50
     Aguilar
    -0.50
     poza
    -0.47
     وضع
    -0.47
     Sieger
    -0.47
     Arzt
    -0.46
     Lage
    -0.46
     Sena
    -0.46
     chapa
    -0.46
    POSITIVE LOGITS
    InputBorder
    0.76
     ſou
    0.74
     dezelve
    0.70
     feroit
    0.69
     ſon
    0.68
     ſche
    0.67
     belangrij
    0.67
     ſtre
    0.65
    iſter
    0.65
     purpoſe
    0.65
    Activations Density 3.681%

    No Known Activations