© 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 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. 3030
    Prev
    Next
    INDEX
    Explanations

    names and affiliations of authors or researchers in a study

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

    Chinese names

    np_acts-logits-general · gemini-2.0-flash

    pinyin syllables followed by surnames

    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
     typelib
    -0.68
     NSCoder
    -0.63
    thums
    -0.60
     مشين
    -0.56
    ifolium
    -0.53
    +#+#
    -0.52
    endphp
    -0.52
    ltk
    -0.52
    恐
    -0.50
    
    -0.50
    POSITIVE LOGITS
     régulier
    0.44
     Majefty
    0.38
     ſtate
    0.37
     sengaja
    0.36
     desmotivaciones
    0.36
     ecológico
    0.36
     domestique
    0.34
     Jepang
    0.34
     ulang
    0.33
     espirituales
    0.33
    Activations Density 0.404%

    No Known Activations