© 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. 12506
    Prev
    Next
    INDEX
    Explanations

    standardized formatting cues in text

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

    Sentences ending with a period

    np_acts-logits-general · gemini-2.0-flash

    sentence ending

    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
    何より
    -0.87
     tudi
    -0.73
     Apalagi
    -0.72
     esimerkiksi
    -0.70
     jopa
    -0.70
    むしろ
    -0.69
     myös
    -0.67
    それでも
    -0.63
    だからこそ
    -0.63
    逆に
    -0.62
    POSITIVE LOGITS
     Briefly
    0.93
     Originally
    0.89
     Previously
    0.87
     Allí
    0.83
     originally
    0.82
    Specifically
    0.80
     Specifically
    0.80
     Essentially
    0.78
    Essentially
    0.77
     Its
    0.77
    Activations Density 0.628%

    No Known Activations