© 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. 0-GEMMASCOPE-RES-16K
    6. 10981
    Prev
    Next
    INDEX
    Explanations

    terms related to assets and equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OMITBAD
    -0.51
    setOnAction
    -0.37
    KURZBESCHREIBUNG
    -0.37
    reactstrap
    -0.35
     Coalition
    -0.35
     tháng
    -0.34
     Flower
    -0.34
     frère
    -0.33
    cVar
    -0.32
     Chamber
    -0.32
    POSITIVE LOGITS
     equip
    1.14
    equip
    1.05
     Equip
    0.97
     equipment
    0.90
    Equip
    0.89
     echip
    0.85
    equipment
    0.85
    Equipment
    0.82
     equipping
    0.81
     équipements
    0.80
    Activations Density 0.278%

    No Known Activations