© 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. 1306
    Prev
    Next
    INDEX
    Explanations

    segments related to programming or technical processes

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

    references to specific individuals or entities

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

    x, surface, ^, content

    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
     Whilst
    -0.93
    Whilst
    -0.92
     whilst
    -0.79
     eighteen
    -0.72
     Firstly
    -0.72
    Firstly
    -0.70
     twenty
    -0.68
     twelve
    -0.68
     nineteenth
    -0.66
    اعمال
    -0.65
    POSITIVE LOGITS
     ¦
    0.83
    “(
    0.77
    TagMode
    0.73
    ¦
    0.72
    basicConfig
    0.71
     Gov
    0.69
     “(
    0.68
     oprot
    0.68
    ◗
    0.67
     ••
    0.67
    Activations Density 0.050%

    No Known Activations