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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7128
    Prev
    Next
    INDEX
    Explanations

    figures and numerical data in scientific text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rhestr
    -0.69
    AnimationsModule
    -0.66
     ویکی‌آمباردا
    -0.63
     '\\;'
    -0.61
    thmetic
    -0.59
    barb
    -0.58
    carded
    -0.58
    +#+
    -0.57
    estroyer
    -0.57
     EconPapers
    -0.56
    POSITIVE LOGITS
    XmlAccessType
    0.35
     kohdetta
    0.35
    <bos>
    0.33
    -------------</
    0.30
     itself
    0.28
     leggen
    0.28
     thus
    0.27
     advantages
    0.27
     zwłaszcza
    0.26
     voordelen
    0.25
    Activations Density 1.284%

    No Known Activations