© 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. 35-GEMMASCOPE-RES-16K
    11. 6924
    Prev
    Next
    INDEX
    Explanations

    terms and references related to political investigations and committees

    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
    setVerticalGroup
    -0.93
    tagHelperRunner
    -0.92
    makeConstraints
    -0.84
     CreateTagHelper
    -0.75
    évaluateur
    -0.75
     resourceCulture
    -0.70
    ंदीखरीदारी
    -0.70
     quizá
    -0.69
    ſammen
    -0.69
    :✨
    -0.69
    POSITIVE LOGITS
     XNUMX
    1.16
     ​​
    1.10
    ̵
    0.83
    ⁇
    0.65
    ​​
    0.61
    NUMX
    0.60
     ™
    0.50
     analyzes
    0.49
     ■
    0.47
     և
    0.46
    Activations Density 0.185%

    No Known Activations