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. 2317
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparisons or relationships between two entities or elements

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

    "between" followed by two objects

    np_acts-logits-general · gemini-2.0-flash

    between two

    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
     allemaal
    -0.62
    Thirty
    -0.53
     ddelweddau
    -0.48
    原始内容存档于
    -0.46
    fetchall
    -0.46
    دهم
    -0.46
    цима
    -0.45
    algunos
    -0.45
    viana
    -0.44
    Others
    -0.44
    POSITIVE LOGITS
     two
    2.75
    two
    2.34
     deux
    2.07
    Two
    2.04
     Two
    1.96
     TWO
    1.88
    TWO
    1.88
     zwei
    1.85
    两个
    1.77
     dwóch
    1.77
    Activations Density 1.212%

    No Known Activations