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. 3-GEMMASCOPE-RES-16K
    6. 10878
    Prev
    Next
    INDEX
    Explanations

    instances of the word "perhaps" or similar uncertain language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     girl
    -0.75
     guy
    -0.75
    gomery
    -0.72
     kids
    -0.72
    gdx
    -0.72
     Ral
    -0.72
     Brenda
    -0.71
     Morena
    -0.71
    cademic
    -0.71
     Andrey
    -0.70
    POSITIVE LOGITS
     perhaps
    1.75
    perhaps
    1.65
     Perhaps
    1.58
    Perhaps
    1.55
     quizás
    1.05
     quizá
    0.95
     belki
    0.95
     doubtless
    0.85
     dunque
    0.84
     arguably
    0.79
    Activations Density 0.042%

    No Known Activations