© 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. 8957
    Prev
    Next
    INDEX
    Explanations

    references to organizations or companies, particularly those denoted with the "&" symbol

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

    "&" followed by a letter

    np_acts-logits-general · gemini-2.0-flash

    abbreviations, initials, and acronyms

    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
    tagHelperRunner
    -0.82
    Hozzáférés
    -0.65
    maakt
    -0.61
     Folly
    -0.61
    الإنجليزية
    -0.55
    queryInterface
    -0.55
    ſelf
    -0.55
    GEBURTSDATUM
    -0.54
    笑了笑
    -0.53
    tamol
    -0.51
    POSITIVE LOGITS
     EconPapers
    0.63
     становника
    0.60
     GenerationType
    0.58
    frontmatter
    0.57
    avyzd
    0.55
    ﹠
    0.50
    rigin
    0.49
    BufferException
    0.49
    boxylic
    0.48
    dotte
    0.47
    Activations Density 0.092%

    No Known Activations