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. 3106
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or realization

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

    "Oh" at the beginning of sentences

    np_acts-logits-general · gemini-2.0-flash

    "Oh," followed by an addition

    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
     myſelf
    -0.81
     houſe
    -0.80
     themſelves
    -0.77
     himſelf
    -0.71
     itſelf
    -0.69
     Efq
    -0.68
     Majefty
    -0.67
     useRouter
    -0.67
    ſelves
    -0.65
    ſelf
    -0.65
    POSITIVE LOGITS
    Oh
    0.93
     Oh
    0.90
     oh
    0.82
     мәкал
    0.81
     OH
    0.78
     Chwiliwch
    0.76
    oh
    0.73
    OH
    0.68
    __(/*!
    0.66
    ThemeOverlay
    0.65
    Activations Density 0.023%

    No Known Activations