© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9611
    Prev
    Next
    INDEX
    Explanations

    key entities and numbers associated with significant events or entities

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

    Word followed by a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    formal introductions or multilingual content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تانيه
    -0.55
    UrlResolution
    -0.54
    UnusedPrivate
    -0.50
    mergeFrom
    -0.48
    новниш
    -0.47
     فريبيس
    -0.45
    outWeight
    -0.45
    ItemBackground
    -0.44
     оно
    -0.44
     вони
    -0.42
    POSITIVE LOGITS
     okuyayım
    0.59
    
    0.42
     CURIAM
    0.38
    ⃣
    0.38
     стра
    0.37
    Newswire
    0.37
    Espèce
    0.37
    PRWEB
    0.36
    ‌پدی
    0.36
    Upon
    0.36
    Activations Density 0.547%

    No Known Activations