Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6232
    Prev
    Next
    INDEX
    Explanations

    statements indicating dialogue or quotes attributed to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ocurrido
    -0.29
     ocurrir
    -0.28
     members
    -0.28
     alternatives
    -0.27
     Pu
    -0.27
    čné
    -0.27
     temp
    -0.27
     Millennium
    -0.26
     technologies
    -0.26
     ویکی‌پدی
    -0.25
    POSITIVE LOGITS
    himself
    1.02
     himself
    0.97
     himſelf
    0.96
     Himself
    0.91
     Geiſt
    0.85
     zijne
    0.85
     ſeiner
    0.83
     Efq
    0.82
     ſeinen
    0.81
     Menſchen
    0.81
    Activations Density 0.343%

    No Known Activations