© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3300
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements related to functions and their annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     This
    -0.49
    <eos>
    -0.48
     berangkat
    -0.48
    kura
    -0.48
    цуз
    -0.47
     rara
    -0.47
     obicei
    -0.46
     Clark
    -0.46
    Clark
    -0.46
     это
    -0.45
    POSITIVE LOGITS
    }{|
    4.52
    }{||
    3.03
    
    1.25
     {|
    1.09
    ReusableCell
    1.04
    {|
    1.04
     >=",
    0.94
    roek
    0.94
     AssemblyVersion
    0.92
     pleaſure
    0.92
    Activations Density 0.031%

    No Known Activations