© 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. 9649
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding study limitations and implications for future research

    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
    Біографія
    -0.55
     DYNAMIC
    -0.48
    PyExc
    -0.46
     dyn
    -0.45
    rrggbb
    -0.45
     thermally
    -0.45
    .~(\
    -0.43
    happily
    -0.43
     Dynamic
    -0.43
     dynamically
    -0.42
    POSITIVE LOGITS
    setVerticalGroup
    0.56
     implications
    0.45
    Odkazy
    0.43
    Handlung
    0.39
     dieß
    0.39
    SourceChecksum
    0.38
    OLEAN
    0.37
    ứng
    0.37
     findings
    0.36
     recommandations
    0.35
    Activations Density 0.723%

    No Known Activations