© 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. 30-GEMMASCOPE-RES-16K
    11. 7879
    Prev
    Next
    INDEX
    Explanations

    expressions related to comprehension and understanding

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

    "understand" and its variations

    np_acts-logits-general · gemini-2.0-flash

    understanding how or what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cyfeiriadau
    -0.48
     surla
    -0.45
    AddTagHelper
    -0.42
    Personensuche
    -0.41
     autorytatywna
    -0.41
     Chri
    -0.40
    itsub
    -0.40
    baceous
    -0.40
    fromnode
    -0.39
     Canary
    -0.38
    POSITIVE LOGITS
     understand
    0.82
    understand
    0.79
     Understanding
    0.79
     Understand
    0.78
    Understanding
    0.77
     understanding
    0.76
    understanding
    0.76
    Understand
    0.74
     comprensión
    0.73
     understands
    0.68
    Activations Density 0.106%

    No Known Activations