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. 20-GEMMASCOPE-RES-16K
    6. 10803
    Prev
    Next
    INDEX
    Explanations

    references to marketing practices and concerns in the film industry

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

    Expressing or revealing information

    np_acts-logits-general · gemini-2.0-flash

    tell or share information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addGap
    -0.52
     nahilalakip
    -0.51
    互联网档案馆
    -0.48
    InjectAttribute
    -0.47
    Datuak
    -0.47
     оригіналу
    -0.47
    chyma
    -0.46
    zow
    -0.45
    ConverterFactory
    -0.44
    RegistryLite
    -0.43
    POSITIVE LOGITS
     tell
    1.72
     telling
    1.63
     Tell
    1.53
     disclose
    1.53
    Tell
    1.52
     divul
    1.49
    Telling
    1.48
     TELL
    1.47
     Telling
    1.46
    tell
    1.42
    Activations Density 0.486%

    No Known Activations