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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15885
    Prev
    Next
    INDEX
    Explanations

    instances of lists or enumerations in the text

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

    "List" followed by what to list

    np_acts-logits-general · gemini-2.0-flash

    list the

    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
    MemoryWarning
    -0.77
    imageshack
    -0.73
    MigrationBuilder
    -0.71
    batore
    -0.71
    hoots
    -0.69
    הערות
    -0.68
    Искәрмәләр
    -0.66
    сылкі
    -0.64
     khảo
    -0.64
    VersionUID
    -0.63
    POSITIVE LOGITS
     newList
    0.95
     Lists
    0.85
    mybatisplus
    0.77
     lists
    0.75
     LIST
    0.73
     list
    0.67
     itemList
    0.66
     mList
    0.65
    lists
    0.65
    Lists
    0.63
    Activations Density 0.151%

    No Known Activations