© 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. 30-GEMMASCOPE-RES-16K
    11. 9771
    Prev
    Next
    INDEX
    Explanations

    complex phrases and references related to specific products or entities

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

    containing "um"

    np_acts-logits-general · gemini-2.0-flash

    "um" sound/spelling

    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
    دانشنامهٔ
    -0.69
     cherchés
    -0.60
    XmlAccessType
    -0.59
    featureID
    -0.59
     мәкал
    -0.57
    parsedMessage
    -0.57
     تضيفلها
    -0.57
    يميديا
    -0.55
    AccessorTable
    -0.54
    TagMode
    -0.54
    POSITIVE LOGITS
     Ume
    0.41
     Dum
    0.40
    umos
    0.38
     lum
    0.37
    uman
    0.37
     Hummel
    0.37
     DUM
    0.37
    umo
    0.36
     Tum
    0.36
     Pum
    0.36
    Activations Density 0.252%

    No Known Activations