© 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. 10210
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming constructs involving data and operations

    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
     &___
    -0.47
    出版年
    -0.41
     مرئيه
    -0.41
     ProtoMessage
    -0.39
     quadratic
    -0.38
    parsedMessage
    -0.38
     propOrder
    -0.37
     auxili
    -0.36
     khẩu
    -0.36
    ьаж
    -0.35
    POSITIVE LOGITS
     conversely
    0.76
     Conversely
    0.66
     reverse
    0.62
    Conversely
    0.60
     sebaliknya
    0.60
     наоборот
    0.59
     umgekehrt
    0.59
    逆に
    0.59
     opposite
    0.59
    opposite
    0.55
    Activations Density 1.016%

    No Known Activations