© 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 EvalsExportsAPI 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. 5359
    Prev
    Next
    INDEX
    Explanations

    concepts related to personal responsibilities and consequences

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

    meaning "too" or "excessively"

    np_acts-logits-general · gemini-2.0-flash

    too much / excess

    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
    ">//
    -0.41
    帖最后由
    -0.36
    Tembelea
    -0.36
    Hentet
    -0.35
    رفته
    -0.34
     respectable
    -0.33
     defaultstate
    -0.33
     прекрасно
    -0.33
    mste
    -0.32
    OGND
    -0.32
    POSITIVE LOGITS
     too
    2.28
     Too
    2.05
    Too
    2.02
    too
    2.02
     TOO
    1.98
     terlalu
    1.91
     слишком
    1.89
     demasiado
    1.81
     excessively
    1.77
     demasi
    1.70
    Activations Density 0.824%

    No Known Activations