© 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. 8281
    Prev
    Next
    INDEX
    Explanations

    references to biological processes and mechanisms

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

    Follows "is," "was," "are," or "were."

    np_acts-logits-general · gemini-2.0-flash

    forms of "to be" followed by state

    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
    AndEndTag
    -0.45
    hical
    -0.45
     Bekannt
    -0.44
     evitare
    -0.43
     Cursed
    -0.43
     kanyang
    -0.42
     Guilt
    -0.41
    seamnă
    -0.41
     thither
    -0.41
    bulos
    -0.41
    POSITIVE LOGITS
     dependent
    0.96
     Dependent
    0.79
     dependant
    0.77
     influenced
    0.74
    IUrlHelper
    0.72
     affected
    0.70
     Roskov
    0.69
     depend
    0.69
    tagHelperRunner
    0.67
     dépend
    0.66
    Activations Density 0.915%

    No Known Activations