© 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. 33-GEMMASCOPE-RES-16K
    11. 9661
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific modeling and boundary conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    schul
    -0.42
     MatDialog
    -0.41
    どうも
    -0.39
    rawDesc
    -0.38
    -------------</
    -0.37
    +#+#
    -0.36
    Apparently
    -0.35
    LookAndFeel
    -0.35
    mont
    -0.35
    Linq
    -0.35
    POSITIVE LOGITS
     boundary
    1.25
     Boundary
    1.02
    boundary
    0.96
     boundaries
    0.95
    边界
    0.93
    Boundary
    0.93
     Boundaries
    0.87
    boundaries
    0.79
    境界
    0.76
    Boundaries
    0.75
    Activations Density 1.502%

    No Known Activations