Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1113
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and personal connections

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

    going to / having / going

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    SequentialGroup
    -0.85
    ChildScrollView
    -0.80
     تضيفلها
    -0.75
    AndEndTag
    -0.74
     незавершена
    -0.70
     EconPapers
    -0.70
     समीक्षाओं
    -0.69
    PyExc
    -0.69
     برانيه
    -0.69
    posedge
    -0.69
    POSITIVE LOGITS
     coming
    1.11
     going
    1.10
    Going
    0.96
     returning
    0.95
     Going
    0.92
     Coming
    0.91
    Coming
    0.90
    coming
    0.89
    going
    0.88
     GOING
    0.85
    Activations Density 0.176%

    No Known Activations