© 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. 3598
    Prev
    Next
    INDEX
    Explanations

    terms related to serious issues or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "serious" in various contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    ReusableCell
    -0.61
     umbi
    -0.56
     handball
    -0.56
    ChildScrollView
    -0.54
    ########.
    -0.54
     Empathy
    -0.53
     Tile
    -0.52
     Paddle
    -0.52
     empathy
    -0.52
     Retailer
    -0.51
    POSITIVE LOGITS
     serious
    1.21
    Serious
    1.21
    serious
    1.19
     Serious
    1.16
     seriously
    1.08
     poważ
    0.96
    seriously
    0.91
     serio
    0.90
     serius
    0.89
     seriousness
    0.85
    Activations Density 0.038%

    No Known Activations