© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6597
    Prev
    Next
    INDEX
    Explanations

    instances of conversation involving interpersonal relationships, attraction, and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following indefinite articles

    np_acts-logits-general · gemini-2.0-flash

    stranger or unfamiliar person

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -0.77
    =$?
    -0.75
    addContainerGap
    -0.73
    setVerticalGroup
    -0.72
    }))
    -0.71
    ponge
    -0.70
    Viitteet
    -0.68
    }]
    -0.66
    }),
    -0.66
    }],
    -0.65
    POSITIVE LOGITS
     strangers
    1.25
     stranger
    1.19
    stranger
    0.95
    陌生
    0.95
     random
    0.93
     Strangers
    0.91
     незна
    0.89
     unfamiliar
    0.86
     desconhe
    0.85
     desconoc
    0.79
    Activations Density 0.278%

    No Known Activations