© 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. 4353
    Prev
    Next
    INDEX
    Explanations

    expressions of anger and frustration

    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
    ]--;
    -0.48
    "}")
    -0.48
     (;;)
    -0.48
    }))
    -0.48
     gedacht
    -0.47
    šķ
    -0.47
     amazingly
    -0.47
    errHandler
    -0.47
    })));
    -0.46
     wonderfully
    -0.46
    POSITIVE LOGITS
    🖕
    0.80
    Espèce
    0.71
     Hieronymus
    0.65
     traitors
    0.64
     cowards
    0.62
     scum
    0.61
     audacity
    0.61
     bastard
    0.61
     imbec
    0.60
     traitor
    0.60
    Activations Density 0.208%

    No Known Activations