Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12618
    Prev
    Next
    INDEX
    Explanations

    calls to action or directives

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

    Action words (verbs) at the start of clauses

    np_acts-logits-general · gemini-2.0-flash

    verbs followed by prepositions

    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
     ainsi
    -0.62
     sowie
    -0.56
     valamint
    -0.54
     maupun
    -0.53
    sowie
    -0.51
     وكذلك
    -0.51
    ırken
    -0.51
     nonché
    -0.50
     Außerdem
    -0.50
     oraz
    -0.50
    POSITIVE LOGITS
     ולה
    0.86
     فريبيس
    0.76
    并
    0.71
    して
    0.69
    並
    0.65
    서
    0.64
    بوابة
    0.63
     незавершена
    0.61
    </caption>
    0.59
     Вікі
    0.58
    Activations Density 0.553%

    No Known Activations