© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 4172
    Prev
    Next
    INDEX
    Explanations

    references to religious or moral concepts in discussions of human relationships

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

    Letters and punctuation

    np_acts-logits-general · gemini-2.0-flash

    places and citations

    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
     houſe
    -0.95
     myſelf
    -0.95
     raiſ
    -0.91
     purpoſe
    -0.90
     pleaſure
    -0.88
     deſt
    -0.87
     themſelves
    -0.85
     iſt
    -0.83
     ſta
    -0.83
     uſe
    -0.82
    POSITIVE LOGITS
     k
    0.91
     z
    0.89
     ch
    0.88
     li
    0.79
     j
    0.78
     m
    0.78
     y
    0.76
     g
    0.75
     c
    0.74
     ma
    0.74
    Activations Density 0.552%

    No Known Activations