© 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. 604
    Prev
    Next
    INDEX
    Explanations

    present participles and gerunds in context

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

    gerunds and action-related words that signify processes or transformations

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

    action or process followed by context

    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
    validated
    -0.49
    komsten
    -0.42
    Westfalen
    -0.41
    enerated
    -0.40
    setAlignment
    -0.40
     étrangère
    -0.39
     seduta
    -0.38
     atuação
    -0.38
     hipó
    -0.38
     darbu
    -0.38
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.92
    WithIOException
    0.85
    SizeF
    0.83
    AddTagHelper
    0.76
    sidemargin
    0.74
    unknownFields
    0.74
     raiſ
    0.72
    Personensuche
    0.71
    BufferException
    0.70
    UserScript
    0.70
    Activations Density 0.097%

    No Known Activations