© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4648
    Prev
    Next
    INDEX
    Explanations

    the term "crazy" and its contextual variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.81
    IsContent
    -0.79
    rxjs
    -0.70
    meneu
    -0.70
    multicolumn
    -0.68
    tableFuture
    -0.67
    ]")]
    -0.65
    MessageOf
    -0.64
     Préférences
    -0.63
    writeFieldEnd
    -0.63
    POSITIVE LOGITS
     insane
    0.79
     crazy
    0.79
     mad
    0.75
    Crazy
    0.71
     silly
    0.70
     MAD
    0.68
     wacky
    0.67
     madness
    0.66
     Crazy
    0.65
     Mad
    0.65
    Activations Density 0.296%

    No Known Activations