Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12798
    Prev
    Next
    INDEX
    Explanations

    expressions of apology and regret

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

    Apologies and expressions of regret

    np_acts-logits-general · gemini-2.0-flash

    apologies and excuses

    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
     autorytatywna
    -0.84
    awtextra
    -0.82
    ]='\
    -0.68
    yntaxException
    -0.67
     "..\..\..\
    -0.65
    ientôt
    -0.64
     FetchType
    -0.64
    TintMode
    -0.63
     makeStyles
    -0.63
    protoimpl
    -0.61
    POSITIVE LOGITS
     apologise
    0.66
     apologised
    0.65
     excuses
    0.64
     excuse
    0.61
     apology
    0.59
     apologize
    0.59
     offend
    0.59
    Sorry
    0.58
     sorry
    0.58
    excuse
    0.57
    Activations Density 0.037%

    No Known Activations