© 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. 2-GEMMASCOPE-RES-16K
    11. 6365
    Prev
    Next
    INDEX
    Explanations

    profanity and explicit sexual language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.53
    CascadeType
    -0.39
     Geduld
    -0.38
    allenge
    -0.37
    せっかく
    -0.37
     discourage
    -0.34
    atalos
    -0.34
    :].
    -0.34
    Female
    -0.34
    agaimana
    -0.33
    POSITIVE LOGITS
     fucking
    1.80
    fucking
    1.59
     Fucking
    1.57
     FUCKING
    1.55
     fuckin
    1.51
     fuck
    1.48
     fucked
    1.47
    fuck
    1.45
     shit
    1.41
    Fucking
    1.41
    Activations Density 0.156%

    No Known Activations