© 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. 16-GEMMASCOPE-RES-16K
    11. 12376
    Prev
    Next
    INDEX
    Explanations

    references to objects, attributes, and conditions in programming or logical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    setVerticalGroup
    -0.41
    Contato
    -0.40
     praktijk
    -0.40
    înd
    -0.37
     Zwer
    -0.37
    anniversaire
    -0.36
    Patrol
    -0.36
     balanced
    -0.35
     curiosidad
    -0.35
     progressive
    -0.34
    POSITIVE LOGITS
     StatelessWidget
    0.56
    TestBed
    0.54
    ंदीखरीदारी
    0.52
    +#+#
    0.46
     simplifié
    0.45
     ReactDOM
    0.42
    IContainer
    0.42
    UMBIA
    0.42
     soles
    0.42
    roidery
    0.42
    Activations Density 0.589%

    No Known Activations