© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11515
    Prev
    Next
    INDEX
    Explanations

    specific names and entities, particularly those related to individuals and their affiliations

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

    Proper nouns followed by specific punctuation or Japanese grammar

    np_acts-logits-general · gemini-2.0-flash

    names and abbreviations

    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
    er
    -0.66
    readObject
    -0.60
     Pineda
    -0.56
    stdlib
    -0.55
     Jimenez
    -0.55
    】:
    -0.54
     UserDao
    -0.53
    cellaneous
    -0.50
     deleteById
    -0.49
    bentar
    -0.49
    POSITIVE LOGITS
    ViewInit
    0.53
    idge
    0.51
    ヨーク
    0.50
    yth
    0.49
    Nucl
    0.49
     paille
    0.48
     Riley
    0.47
    massen
    0.45
    y
    0.45
    postIndex
    0.45
    Activations Density 2.929%

    No Known Activations