© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 9198
    Prev
    Next
    INDEX
    Explanations

    concepts related to discussions and communication around sensitive topics

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

    followed by "topic" or "subject"

    np_acts-logits-general · gemini-2.0-flash

    this topic

    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
    SharedDtor
    -0.60
     дописавши
    -0.56
    writeFieldEnd
    -0.56
    XtraReports
    -0.55
    перь
    -0.54
    inerja
    -0.52
    FontOfSize
    -0.52
     Wicidata
    -0.51
     rhestr
    -0.49
     DASH
    -0.49
    POSITIVE LOGITS
     topic
    3.20
     subject
    3.00
     theme
    2.83
     topics
    2.64
     Topic
    2.63
    subject
    2.52
    Topic
    2.51
     Subject
    2.47
    topic
    2.47
     themes
    2.43
    Activations Density 0.339%

    No Known Activations