© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1280
    Prev
    Next
    INDEX
    Explanations

    instances of movement or changes in position, particularly in a repetitive or oscillating manner

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

    phrases indicating repetitive actions or changes

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

    movement and direction changes

    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
    /
    -0.56
     first
    -0.50
     one
    -0.48
     
    -0.47
     M
    -0.45
     R
    -0.45
    cret
    -0.43
     duy
    -0.42
     Al
    -0.42
     all
    -0.41
    POSITIVE LOGITS
     <=",
    1.32
     autorytatywna
    1.11
    NameInMap
    1.05
    WaitGroup
    1.02
    expandindo
    1.01
     تضيفلها
    1.01
    enumii
    0.98
    AddTagHelper
    0.98
     Мексичка
    0.97
    mybatisplus
    0.96
    Activations Density 0.057%

    No Known Activations