© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 1697
    Prev
    Next
    INDEX
    Explanations

    experiences related to physical discomfort or labor pains

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

    First-person narratives and commas

    np_acts-logits-general · gemini-2.0-flash

    continuous or repeated actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Daily
    -0.40
     Week
    -0.38
    Daily
    -0.35
    IRON
    -0.34
     certification
    -0.34
     weeks
    -0.33
    Weeks
    -0.33
     ferru
    -0.32
     دهنده
    -0.32
     デイ
    -0.32
    POSITIVE LOGITS
     constantly
    1.00
     continually
    0.93
     constantemente
    0.88
     intermittently
    0.88
    不时
    0.86
     constamment
    0.84
     continuously
    0.84
     folyam
    0.83
     periodically
    0.80
     continuamente
    0.80
    Activations Density 0.473%

    No Known Activations