© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 8156
    Prev
    Next
    INDEX
    Explanations

    phrases related to warranties and guarantees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasColumnName
    -0.33
    AnimationsModule
    -0.31
    お疲れ
    -0.29
     Nadel
    -0.29
    webElementXpaths
    -0.28
     semula
    -0.27
    */].
    -0.27
     almendras
    -0.27
    getOut
    -0.26
    pgterms
    -0.25
    POSITIVE LOGITS
     guarantee
    3.08
     guarantees
    2.81
     guaranteed
    2.73
    guarantee
    2.69
     Guarantee
    2.66
    Guarantee
    2.55
     guaranteeing
    2.48
    guar
    2.47
     Guarante
    2.45
     guaranty
    2.39
    Activations Density 0.513%

    No Known Activations