© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8154
    Prev
    Next
    INDEX
    Explanations

    terms related to tax liability and employment classifications

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

    Legal or contractual provisions

    np_acts-logits-general · gemini-2.0-flash

    legal or technical context

    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
     lenker
    -0.70
     estimés
    -0.67
    arXiv
    -0.62
     kasarigan
    -0.60
    OCCURRED
    -0.58
    
    -0.57
    /"
    -0.57
    albeit
    -0.57
     ungkapnya
    -0.57
    存于互联网档案馆
    -0.56
    POSITIVE LOGITS
    つて
    0.63
    —.
    0.56
     Audiodateien
    0.54
    numerusform
    0.53
     cesse
    0.51
    —
    0.51
     nhiêu
    0.50
     getrennt
    0.49
    oker
    0.49
    цездатний
    0.48
    Activations Density 0.639%

    No Known Activations