© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 12790
    Prev
    Next
    INDEX
    Explanations

    references to specific technical components or variables in programming code

    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
    setContentView
    -0.82
     offense
    -0.35
    KommentareTeilen
    -0.35
     gemis
    -0.33
    enumii
    -0.33
    💼
    -0.33
     do
    -0.33
     meille
    -0.32
     dö
    -0.32
    setPrice
    -0.31
    POSITIVE LOGITS
    @[+][
    6.75
    aarrggbb
    2.00
     '\\;'
    1.65
    PreferredItem
    1.44
     defaultstate
    1.09
    bitField
    1.06
    rrggbb
    1.04
    millimeters
    1.00
    adaptiveStyles
    0.97
    yarnpkg
    0.88
    Activations Density 0.001%

    No Known Activations