© 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. 7857
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document

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

    Following "Q:" or numbers

    np_acts-logits-general · gemini-2.0-flash

    birth dates and family status

    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
     autorytatywna
    -0.66
     *__
    -0.61
    :✨
    -0.61
     bezeichneter
    -0.57
    msgTypes
    -0.57
    
    -0.56
     يتيمه
    -0.56
    rimin
    -0.56
    Rather
    -0.53
    Hozzáférés
    -0.52
    POSITIVE LOGITS
     predeceased
    0.92
    deceased
    0.70
     whom
    0.70
    whom
    0.61
     residing
    0.61
     wife
    0.60
     deceased
    0.60
    married
    0.59
     married
    0.59
     spouse
    0.57
    Activations Density 0.055%

    No Known Activations