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. 5279
    Prev
    Next
    INDEX
    Explanations

    IT-related technical specifications and parameters

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

    Verilog/hardware chip designs and parameters

    np_acts-logits-general · gemini-2.0-flash

    multiple cores or chips

    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
    脚注の使い方
    -0.59
     GUS
    -0.50
    ẵn
    -0.50
    Personensuche
    -0.49
    Demografie
    -0.48
    tomcat
    -0.47
    GUS
    -0.47
    ypeł
    -0.46
     Colli
    -0.45
     übers
    -0.44
    POSITIVE LOGITS
     chip
    0.73
     veril
    0.69
    designs
    0.69
    design
    0.67
     design
    0.65
    PerformLayout
    0.65
     FPGA
    0.64
     designs
    0.63
     chips
    0.63
     Chip
    0.63
    Activations Density 0.762%

    No Known Activations