© 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. 5398
    Prev
    Next
    INDEX
    Explanations

    words that describe high-quality attributes or characteristics in various contexts

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

    ending in "-self" or foreign words

    np_acts-logits-general · gemini-2.0-flash

    descriptive adjectives followed by nouns

    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
     évent
    -0.46
     hoped
    -0.46
     enz
    -0.45
     eller
    -0.44
     sort
    -0.44
     later
    -0.44
     rất
    -0.44
     atau
    -0.43
     else
    -0.43
    ){\
    -0.43
    POSITIVE LOGITS
     themſelves
    0.87
    ſelf
    0.86
     myſelf
    0.83
     itſelf
    0.82
     himſelf
    0.80
     disambiguazione
    0.78
    Personensuche
    0.76
    oa̍t
    0.75
     purpoſe
    0.74
     whoſe
    0.72
    Activations Density 0.148%

    No Known Activations