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. 6368
    Prev
    Next
    INDEX
    Explanations

    references to people and their relationships or possessions

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

    Possessive form of pronouns and nouns

    np_acts-logits-general · gemini-2.0-flash

    possessives followed by human concepts

    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
     you
    -0.60
     two
    -0.59
     couple
    -0.57
    you
    -0.57
    期刊论文
    -0.55
    two
    -0.52
     lui
    -0.50
    好处
    -0.49
    的两
    -0.49
     dvoj
    -0.47
    POSITIVE LOGITS
    ✨:
    1.02
     their
    0.91
    their
    0.89
     resourceCulture
    0.86
    цездатний
    0.85
    verwijspagina
    0.85
    Rhestr
    0.84
    Their
    0.82
     Мексичка
    0.81
    SPATH
    0.80
    Activations Density 0.241%

    No Known Activations