© 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. 6006
    Prev
    Next
    INDEX
    Explanations

    terms related to jury selection and evaluation processes

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

    after prepositions or symbols

    np_acts-logits-general · gemini-2.0-flash

    symbols and specific terms

    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
    NUMX
    -1.11
    .",
    -1.05
      
    -1.02
    ."]
    -1.01
    ,»
    -0.99
    ".
    -0.99
    .[/
    -0.98
    . 
    -0.97
    ,'"
    -0.96
     ⁠
    -0.95
    POSITIVE LOGITS
     =
    1.15
     &
    1.12
     ->
    1.06
     ppl
    0.97
     govt
    0.94
     =>
    0.89
    !!
    0.88
    :
    0.88
    !!!
    0.87
    ->
    0.86
    Activations Density 0.399%

    No Known Activations