© 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. 9957
    Prev
    Next
    INDEX
    Explanations

    affirmations and positive descriptors related to various subjects

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

    Preceding adjectives of quality

    np_acts-logits-general · gemini-2.0-flash

    simply extreme positive adjectives

    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
    
    -0.75
    HasAnnotation
    -0.73
    ISupport
    -0.68
     Efq
    -0.65
     <=",
    -0.64
    Clik
    -0.63
    WithMany
    -0.62
     chofe
    -0.62
    Viel
    -0.61
     незавершена
    -0.61
    POSITIVE LOGITS
     amazing
    1.71
     incredible
    1.69
     phenomenal
    1.65
     AMAZING
    1.59
     fantastic
    1.50
     extraordinary
    1.46
     unbelievable
    1.44
    amazing
    1.42
    incredible
    1.42
     Incredible
    1.42
    Activations Density 0.359%

    No Known Activations