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. 12732
    Prev
    Next
    INDEX
    Explanations

    phrases indicating capability or competence

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

    "capable of"

    np_acts-logits-general · gemini-2.0-flash

    capable of

    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
    endphp
    -0.98
     betweenstory
    -0.82
    LookAnd
    -0.78
    WindowConstants
    -0.77
    AndEndTag
    -0.75
    MENAFN
    -0.70
    Personensuche
    -0.70
    encodeWith
    -0.70
    IContainer
    -0.68
    ViewFeatures
    -0.67
    POSITIVE LOGITS
     enough
    0.62
     to
    0.55
    ísima
    0.54
     only
    0.54
    kép
    0.52
     geworden
    0.52
    erschein
    0.50
    ísimo
    0.50
     assai
    0.50
    もり
    0.49
    Activations Density 0.950%

    No Known Activations