© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5255
    Prev
    Next
    INDEX
    Explanations

    HTML tags and elements commonly used in web content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.79
    出版年
    -0.71
     estadounid
    -0.64
    Sklici
    -0.63
    kuuta
    -0.63
    Spoljašnje
    -0.63
     indígen
    -0.62
     myſelf
    -0.62
    Autoritní
    -0.60
    fromnode
    -0.60
    POSITIVE LOGITS
    p
    0.75
     p
    0.45
    li
    0.44
    noindent
    0.43
    matchCondition
    0.42
    mtd
    0.40
    <bos>
    0.40
    medskip
    0.40
     endl
    0.40
    hline
    0.39
    Activations Density 0.274%

    No Known Activations