© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 16322
    Prev
    Next
    INDEX
    Explanations

    references to boundary conditions in mathematical or physical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -0.48
     EconPapers
    -0.47
     FetchType
    -0.46
     wireType
    -0.46
    autorest
    -0.40
    fortawesome
    -0.39
     виправивши
    -0.38
    큼
    -0.38
    agisse
    -0.37
    RTLR
    -0.35
    POSITIVE LOGITS
     conditions
    3.64
     Conditions
    3.27
     condition
    3.27
    conditions
    3.20
    Conditions
    3.11
     CONDITIONS
    3.00
     Condition
    2.92
    condition
    2.91
    Condition
    2.75
    条件
    2.75
    Activations Density 1.122%

    No Known Activations