© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 240
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to patient demographics and experimental conditions

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

    about variation or range of values

    np_acts-logits-general · gemini-2.0-flash

    describing ranges of values

    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
    служ
    -0.41
    ณะ
    -0.39
     groupBox
    -0.39
    ред
    -0.38
     ==
    -0.38
     sam
    -0.37
    webElementXpaths
    -0.37
     stoff
    -0.36
    heureusement
    -0.36
    cur
    -0.35
    POSITIVE LOGITS
     ranging
    2.18
     range
    1.99
     ranges
    1.94
     ranged
    1.89
    ranging
    1.85
     Range
    1.75
    range
    1.72
     RANGE
    1.72
    Range
    1.65
     Ranges
    1.62
    Activations Density 0.798%

    No Known Activations