© 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. 7247
    Prev
    Next
    INDEX
    Explanations

    concepts related to nurturing and supportive parenting methods

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

    Polite requests or questions

    np_acts-logits-general · gemini-2.0-flash

    asking questions and listening politely

    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
     torchvision
    -0.69
     الرياضيه
    -0.67
    aarrggbb
    -0.65
    ComponentScan
    -0.64
     للمعارف
    -0.58
     MotionEvent
    -0.58
     destino
    -0.57
    migrationBuilder
    -0.57
    MultipartFile
    -0.57
     rêver
    -0.56
    POSITIVE LOGITS
     tact
    0.90
     politely
    0.87
     empathetic
    0.82
     conversational
    0.80
     rapport
    0.80
     respectful
    0.79
     polite
    0.79
     empathy
    0.79
     politeness
    0.75
     conversation
    0.75
    Activations Density 0.673%

    No Known Activations