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. 3643
    Prev
    Next
    INDEX
    Explanations

    statements related to AWS IAM roles and permissions

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

    "Amazon" or AWS services

    np_acts-logits-general · gemini-2.0-flash

    amazon aws services

    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
    numerusform
    -0.73
    omla
    -0.60
     ballast
    -0.60
    zeczy
    -0.60
     Korn
    -0.60
    hoek
    -0.58
    Korn
    -0.58
     Pastel
    -0.56
    ỡng
    -0.56
    ScopeManager
    -0.56
    POSITIVE LOGITS
     Amazon
    1.70
    Amazon
    1.52
     amazon
    1.42
     AMAZON
    1.28
    amazon
    1.19
     AWS
    1.15
    AMAZ
    1.05
    亚马逊
    1.04
    AWS
    1.04
     Amaz
    1.04
    Activations Density 0.253%

    No Known Activations