© 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. 14-GEMMASCOPE-RES-16K
    11. 7179
    Prev
    Next
    INDEX
    Explanations

    HTML attributes related to resource sources like images or scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "-";
    -0.60
    openzeppelin
    -0.59
    tinger
    -0.59
     Winder
    -0.58
    Дереккөздер
    -0.56
    exitRule
    -0.56
     Hound
    -0.56
     ?>">
    -0.56
     Tif
    -0.56
    Mailer
    -0.56
    POSITIVE LOGITS
    src
    1.47
     src
    1.46
    Src
    1.09
     Src
    0.96
     SRC
    0.89
    SRC
    0.81
    srcs
    0.57
     dst
    0.54
    RunWith
    0.52
    dst
    0.52
    Activations Density 0.058%

    No Known Activations