© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6921
    Prev
    Next
    INDEX
    Explanations

    elements related to a checklist or list-making.

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

    references to personal experiences and accomplishments.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to bucket lists, to-do lists, or completing goals/tasks.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    HTML list tags (ul, ol, li) and "list" as a concept

    np_acts-logits-general · gemini-2.0-flash

    my list

    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
     unknownFields
    -0.68
    IUrlHelper
    -0.63
    WindowEvent
    -0.58
    NameInMap
    -0.54
    IsContent
    -0.53
    setVerticalGroup
    -0.52
    GeneratedCode
    -0.52
    ربای
    -0.52
    OGND
    -0.51
     مشين
    -0.51
    POSITIVE LOGITS
     list
    2.35
    list
    1.94
     lists
    1.91
     List
    1.80
     LIST
    1.74
     lista
    1.66
     liste
    1.60
    LIST
    1.60
     Lists
    1.58
    List
    1.58
    Activations Density 0.356%

    No Known Activations