© 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. 38-GEMMASCOPE-RES-16K
    6. 8561
    Prev
    Next
    INDEX
    Explanations

    self-referential phrases and expressions of sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MathML
    -0.48
    Supported
    -0.32
    supported
    -0.32
    displaystyle
    -0.30
    spoken
    -0.28
    HomeAsUpEnabled
    -0.28
    Received
    -0.28
     witnessed
    -0.28
     bore
    -0.27
     Supported
    -0.26
    POSITIVE LOGITS
     added
    0.99
     Added
    0.95
    added
    0.90
     modified
    0.88
     removed
    0.87
    Added
    0.86
     selected
    0.85
     ADDED
    0.84
     tweaked
    0.83
    removed
    0.82
    Activations Density 0.731%

    No Known Activations