© 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. 20-GEMMASCOPE-RES-16K
    6. 7479
    Prev
    Next
    INDEX
    Explanations

    topics related to governance and institutional integrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.64
    ReusableCell
    -0.63
     OFDb
    -0.57
     PeEnEo
    -0.55
    uxxxx
    -0.54
    httphttps
    -0.54
    TypedDataSet
    -0.54
    pecially
    -0.53
    WithIOException
    -0.49
    Насе
    -0.49
    POSITIVE LOGITS
     tetap
    0.68
    依旧
    0.57
     vẫn
    0.57
     unchanged
    0.54
     remain
    0.53
    変わらず
    0.51
     same
    0.50
     weiterhin
    0.50
     remains
    0.50
     unaltered
    0.48
    Activations Density 0.358%

    No Known Activations