© 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. 1-GEMMASCOPE-RES-16K
    6. 8611
    Prev
    Next
    INDEX
    Explanations

    terms related to tubes and tubular structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.71
    RTCK
    -0.57
    MemoryWarning
    -0.55
    ANTLR
    -0.54
    tagHelperRunner
    -0.48
    tagext
    -0.46
    HttpFoundation
    -0.45
    SourceChecksum
    -0.45
    Personensuche
    -0.45
     Ehr
    -0.44
    POSITIVE LOGITS
     tub
    0.62
     cylinders
    0.56
    ules
    0.53
     Tub
    0.53
     cylinder
    0.52
     Cylinder
    0.52
    ule
    0.52
    tub
    0.50
     Bub
    0.50
     Cyl
    0.49
    Activations Density 0.532%

    No Known Activations