© 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. 6361
    Prev
    Next
    INDEX
    Explanations

    references to relationships and personal connections

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

    Follows a noun indicating a person and a verb

    np_acts-logits-general · gemini-2.0-flash

    friend offered or taught

    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
     }}">
    -0.61
    CrossRef
    -0.61
     CGRect
    -0.56
    脚注の使い方
    -0.56
     AdapterView
    -0.55
    AccessorTable
    -0.52
    Datuak
    -0.52
    EClass
    -0.50
    RTSN
    -0.50
    "]),
    -0.50
    POSITIVE LOGITS
     suggested
    1.05
     kindly
    0.96
     invited
    0.94
     told
    0.94
     graciously
    0.90
     offered
    0.89
     asked
    0.86
     taught
    0.86
     generously
    0.83
     advised
    0.81
    Activations Density 0.404%

    No Known Activations