© 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. 10550
    Prev
    Next
    INDEX
    Explanations

    terms related to institutions and organizations involved in research and higher education

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

    Plural nouns ending in "s" referring to institutions

    np_acts-logits-general · gemini-2.0-flash

    organizations and their functions

    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
    parsedMessage
    -1.05
    archiviato
    -0.73
     محفوظة
    -0.73
    InSection
    -0.73
     виправивши
    -0.72
    AndEndTag
    -0.71
    (!__
    -0.70
    IsMutable
    -0.69
     Paglinawan
    -0.69
     BoxDecoration
    -0.68
    POSITIVE LOGITS
     whose
    0.84
     who
    0.83
     specializing
    0.79
     interested
    0.74
     operating
    0.74
     participating
    0.73
     willing
    0.69
     specialising
    0.69
    whose
    0.69
     engaged
    0.66
    Activations Density 0.378%

    No Known Activations