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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9738
    Prev
    Next
    INDEX
    Explanations

    references to specific timing and measurement parameters in control systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ScopeManager
    -0.65
    AndEndTag
    -0.65
    MemoryWarning
    -0.65
    RegressionTest
    -0.64
    ParallelGroup
    -0.61
    NetworkInfo
    -0.61
     GetEnumerator
    -0.60
    AnchorTagHelper
    -0.56
    IntoConstraints
    -0.55
    ⓧ
    -0.55
    POSITIVE LOGITS
     milliseconds
    0.80
     latency
    0.75
     delay
    0.71
     pico
    0.71
     ms
    0.70
     ns
    0.70
     delays
    0.67
     micro
    0.67
     nano
    0.67
    ms
    0.67
    Activations Density 0.697%

    No Known Activations