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. 12043
    Prev
    Next
    INDEX
    Explanations

    expressions of disappointment or negativity

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

    Followed by a comma, "Unfortunately" and similar words

    np_acts-logits-general · gemini-2.0-flash

    unexpected outcomes

    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
    intios
    -0.63
    يميديا
    -0.58
     einzu
    -0.54
    principalColumn
    -0.54
    いかに
    -0.54
    
    -0.54
    ftagPool
    -0.52
    Window
    -0.51
    Crossref
    -0.50
     awakeFromNib
    -0.50
    POSITIVE LOGITS
     Leider
    0.68
    Unfortunately
    0.65
    SourceChecksum
    0.63
     ligiloj
    0.62
    Tembelea
    0.61
     оригіналу
    0.61
     Unfortunately
    0.60
    erweise
    0.60
    Luckily
    0.60
     unlike
    0.59
    Activations Density 0.109%

    No Known Activations