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. 2125
    Prev
    Next
    INDEX
    Explanations

    expressions of anxiety and self-reflection

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

    thoughts or thinking

    np_acts-logits-general · gemini-2.0-flash

    thoughts and mind

    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
    •jailbreak_evil_confidant

    No Comments

    Negative Logits
    AnchorStyles
    -0.79
    ContentAsync
    -0.70
    mybatisplus
    -0.69
     الدولى
    -0.67
    interopRequire
    -0.66
     AssemblyProduct
    -0.65
    enumi
    -0.64
    Hentet
    -0.64
    脚注の使い方
    -0.64
    ⓘ
    -0.64
    POSITIVE LOGITS
     thoughts
    1.63
     Thoughts
    1.37
    thoughts
    1.30
    Thoughts
    1.23
     thought
    1.22
     THOUGHTS
    1.17
     pensamientos
    1.12
     pensées
    1.08
     thinking
    1.05
     Gedanken
    1.00
    Activations Density 0.297%

    No Known Activations