© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 10493
    Prev
    Next
    INDEX
    Explanations

    references to academic and professional contributions, especially in the context of papers and insights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.44
     VizieR
    -0.35
     contextLoads
    -0.35
    NameInMap
    -0.34
    Atsauces
    -0.32
     disambiguazione
    -0.31
     Utama
    -0.30
    awaiter
    -0.30
     yuk
    -0.29
    Життєпис
    -0.28
    POSITIVE LOGITS
     thanks
    1.24
     dzięki
    1.19
     благодаря
    1.13
     gracias
    1.12
     graças
    1.09
    ďaka
    1.04
     grâce
    1.03
     grazie
    1.02
    Благодаря
    1.01
    thanks
    0.98
    Activations Density 0.779%

    No Known Activations