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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 10500
    Prev
    Next
    INDEX
    Explanations

    phrases that describe physical actions and interactions

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

    Movement against something

    np_acts-logits-general · gemini-2.0-flash

    physical contact or collision

    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
    \{\\
    -0.60
    orap
    -0.50
     لات
    -0.47
     separable
    -0.45
    NVIC
    -0.45
    Torna
    -0.43
    loren
    -0.42
    IsTrue
    -0.42
    MLLoader
    -0.41
     Handwerk
    -0.41
    POSITIVE LOGITS
     against
    1.74
    against
    1.56
     Against
    1.51
    Against
    1.51
     AGAINST
    1.30
     contre
    1.19
     tegen
    1.06
     gegen
    0.89
     againſt
    0.85
     hitting
    0.82
    Activations Density 0.229%

    No Known Activations