Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-GEMMASCOPE-RES-16K
    6. 10172
    Prev
    Next
    INDEX
    Explanations

    terms related to configuration and system commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     up
    -0.75
     out
    -0.70
     away
    -0.60
     into
    -0.59
    up
    -0.57
     ↑
    -0.54
     sure
    -0.49
    FromArray
    -0.48
     ex
    -0.48
    SetUp
    -0.47
    POSITIVE LOGITS
     beginnetje
    1.14
    تقاوى
    1.09
    AutoScaleMode
    0.93
     pinulongan
    0.88
    OGND
    0.86
    WebVitals
    0.85
    Personensuche
    0.80
    GraphicsUnit
    0.79
    StoryboardSegue
    0.78
    RTEE
    0.77
    Activations Density 1.499%

    No Known Activations