© 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. 117
    Prev
    Next
    INDEX
    Explanations

    repeated instances of specific numerical or categorical markers in data analysis

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

    Numbers referring to items in a list

    np_acts-logits-general · gemini-2.0-flash

    third ordinal number

    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
     Second
    -0.98
     ②
    -0.90
    Second
    -0.89
     Secondly
    -0.88
    ②
    -0.83
     second
    -0.79
     II
    -0.79
    SECOND
    -0.77
     SECOND
    -0.76
     zweite
    -0.72
    POSITIVE LOGITS
     thirds
    1.04
     Thirdly
    1.02
     third
    0.94
    Third
    0.85
    thirds
    0.84
     Third
    0.84
    third
    0.84
     terceiro
    0.82
     tertiary
    0.81
     thrice
    0.81
    Activations Density 0.878%

    No Known Activations