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. 15665
    Prev
    Next
    INDEX
    Explanations

    details about work experience and professional qualifications

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

    Years of experience

    np_acts-logits-general · gemini-2.0-flash

    years of experience

    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
    ########.
    -0.64
    RenderAtEndOf
    -0.61
    makeConstraints
    -0.54
    textTheme
    -0.54
    zenio
    -0.54
    createCell
    -0.50
    ParallelGroup
    -0.50
     الدولى
    -0.48
     delito
    -0.47
    Obrázky
    -0.47
    POSITIVE LOGITS
     experience
    2.85
    experience
    2.43
     Experience
    2.31
    Experience
    2.28
     EXPERIENCE
    2.23
     expérience
    2.14
     experiences
    2.07
     experiencia
    2.01
    EXPERIENCE
    1.95
     experiência
    1.94
    Activations Density 0.382%

    No Known Activations