© 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. 10-GEMMASCOPE-RES-16K
    11. 14352
    Prev
    Next
    INDEX
    Explanations

    expletives and strong negative language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.42
     yyr
    -0.42
     juſt
    -0.39
    リーフ
    -0.38
     poffible
    -0.37
     Eſ
    -0.37
     whoſe
    -0.36
     Quota
    -0.36
     Natives
    -0.35
     Plans
    -0.35
    POSITIVE LOGITS
     fucking
    1.38
     goddamn
    1.28
    fuck
    1.27
    fucking
    1.25
     fuck
    1.25
     Fucking
    1.23
     fuckin
    1.22
     damn
    1.21
     shit
    1.21
    Fuck
    1.20
    Activations Density 0.282%

    No Known Activations