© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29776
    Prev
    Next
    INDEX
    Explanations

    phrases related to overhead objects or fixtures, particularly lighting

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

    spatial position above or below

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.56
    ArgsConstructor
    -0.48
    asmuch
    -0.48
    numerusform
    -0.46
     yaşında
    -0.44
     meisten
    -0.44
    Referanser
    -0.44
    Ứng
    -0.43
     curva
    -0.42
    ditto
    -0.42
    POSITIVE LOGITS
     utafitiHapana
    0.75
     ISNI
    0.62
     overhead
    0.60
    oredCriteria
    0.60
    Autoritní
    0.58
    Населення
    0.57
    overhead
    0.57
     ceilings
    0.54
     jScrollPane
    0.54
     ceiling
    0.53
    Activations Density 0.107%

    No Known Activations