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. 22-GEMMASCOPE-RES-16K
    6. 12771
    Prev
    Next
    INDEX
    Explanations

    financial data and industry performance metrics

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

    following "has"

    np_acts-logits-general · gemini-2.0-flash

    observing change and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.89
     оригіналу
    -0.79
    Tembelea
    -0.78
     Normdatei
    -0.71
    новништво
    -0.70
    Източници
    -0.68
    躇
    -0.68
    ReusableCell
    -0.67
    +#+#
    -0.66
    تقاوى
    -0.66
    POSITIVE LOGITS
     saw
    1.43
     seeing
    1.34
     witnessing
    1.26
     experienced
    1.26
     sees
    1.23
     experiencing
    1.23
     witnessed
    1.19
     see
    1.18
    saw
    1.13
    seeing
    1.12
    Activations Density 0.336%

    No Known Activations