© 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. 18-GEMMASCOPE-RES-16K
    11. 871
    Prev
    Next
    INDEX
    Explanations

    terms related to product comparisons and customer experiences within a business context

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

    preceding "that," "to," "when," "for," or "of."

    np_acts-logits-general · gemini-2.0-flash

    noun followed by connector

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.84
     protoimpl
    -0.82
    ंदीखरीदारी
    -0.78
     समीक्षक
    -0.75
    verwijspagina
    -0.74
    Aholisi
    -0.74
     allAfrica
    -0.72
     AssemblyTitle
    -0.71
    Demografie
    -0.70
    rrggbb
    -0.70
    POSITIVE LOGITS
     ว่า
    0.54
    ypeł
    0.51
     ότι
    0.50
    postmedia
    0.49
     بأنه
    0.47
    [:]
    0.46
    serviceWorker
    0.46
     PDFs
    0.46
    ([])
    0.45
    来说
    0.45
    Activations Density 1.079%

    No Known Activations