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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1172
    Prev
    Next
    INDEX
    Explanations

    phrases related to frequency and repetition of activities

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

    Frequency or quantity per time period

    np_acts-logits-general · gemini-2.0-flash

    frequency and rates

    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
    
    -0.57
    AutoScaleMode
    -0.53
     pulumi
    -0.49
    CastException
    -0.48
    toBeTruthy
    -0.48
     kep
    -0.47
     MainAxisSize
    -0.44
    TagHelper
    -0.44
     '\\;'
    -0.44
    Ārējās
    -0.44
    POSITIVE LOGITS
     annually
    1.51
     yearly
    1.38
     per
    1.28
     monthly
    1.18
     annual
    1.12
     Yearly
    1.09
     weekly
    1.08
    yearly
    1.03
     anual
    1.02
     year
    0.99
    Activations Density 0.218%

    No Known Activations