© 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. 35-GEMMASCOPE-RES-16K
    11. 15218
    Prev
    Next
    INDEX
    Explanations

    specific details about tire construction and the various rubber components involved

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.63
    FXML
    -0.57
     okuyayım
    -0.55
    󠁢
    -0.54
    IBOutlet
    -0.52
     resourceCulture
    -0.51
     Chwiliwch
    -0.50
    parsedMessage
    -0.48
     InputDecoration
    -0.47
    DrawerToggle
    -0.46
    POSITIVE LOGITS
     tire
    1.68
     tires
    1.66
     tyres
    1.49
     tyre
    1.48
     Tires
    1.41
     Tire
    1.39
    Tire
    1.31
    Tires
    1.22
     Tyres
    1.20
    tires
    1.17
    Activations Density 0.207%

    No Known Activations