© 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. 16-GEMMASCOPE-RES-16K
    11. 4900
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and terminology related to sets and their relationships

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

    Punctuation followed by specific words

    np_acts-logits-general · gemini-2.0-flash

    punctuation followed by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iVar
    -0.61
    andaag
    -0.55
     synonymous
    -0.50
    rache
    -0.49
    best
    -0.48
    httphttps
    -0.48
    amili
    -0.46
    ược
    -0.46
    web
    -0.45
     Thayer
    -0.43
    POSITIVE LOGITS
     tartalomajánló
    0.76
     contradiction
    0.63
     nécessairement
    0.63
    WebElementEntity
    0.62
    !*\
    0.62
     either
    0.59
    bewerken
    0.58
     незавершена
    0.58
    either
    0.56
    σιμοποι
    0.56
    Activations Density 2.202%

    No Known Activations