© 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. 8410
    Prev
    Next
    INDEX
    Explanations

    actions related to helping others and community engagement

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

    Preceding verbs related to giving/telling

    np_acts-logits-general · gemini-2.0-flash

    their and themselves

    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
     them
    -2.00
    them
    -1.69
     THEM
    -1.32
    ándolos
    -1.16
     них
    -1.06
     آنها
    -1.01
     őket
    -0.97
     آن‌ها
    -0.97
     ними
    -0.94
     вони
    -0.92
    POSITIVE LOGITS
     their
    2.15
     themselves
    2.10
    Their
    1.93
    their
    1.86
    themselves
    1.86
     Their
    1.78
     ihre
    1.63
     ihren
    1.60
     THEIR
    1.44
     leurs
    1.34
    Activations Density 0.918%

    No Known Activations