© 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. 8423
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "about" or introductory sections regarding a topic or individual

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

    "About" followed by a noun phrase

    np_acts-logits-general · gemini-2.0-flash

    about headings

    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
     ModelExpression
    -0.77
     houſe
    -0.61
     alſo
    -0.58
     ResponseEntity
    -0.56
     himſelf
    -0.56
     Nw
    -0.55
     Penrose
    -0.55
    깐
    -0.54
    itals
    -0.54
    ral
    -0.54
    POSITIVE LOGITS
    GEBURTSDATUM
    0.88
    SPATH
    0.77
    脚注の使い方
    0.73
     nakalista
    0.71
    enumi
    0.68
     Bout
    0.68
    Tikang
    0.67
    ABOUT
    0.67
    Bout
    0.67
     Bourgoin
    0.66
    Activations Density 0.123%

    No Known Activations