© 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 EvalsExportsinterp-engineNEWAPI 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. 1262
    Prev
    Next
    INDEX
    Explanations

    terms related to business growth and partnerships

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

    business growth or momentum

    np_acts-logits-general · gemini-2.0-flash

    growth and expansion

    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
     Usually
    -0.60
     Worse
    -0.57
     kadang
    -0.54
     Sometimes
    -0.54
     peor
    -0.54
     strangest
    -0.53
     supuestamente
    -0.53
    usually
    -0.52
    Beware
    -0.52
     wierd
    -0.52
    POSITIVE LOGITS
     strengthening
    1.12
     strengthened
    1.11
     strengthen
    1.06
     strengthens
    1.05
    strengthen
    1.05
     expanding
    0.98
     solidif
    0.98
    Strengthen
    0.97
     Strengthen
    0.94
     expansion
    0.91
    Activations Density 0.254%

    No Known Activations