© 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 - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 5381
    Prev
    Next
    INDEX
    Explanations

    present tense and continuous verb forms

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

    after forms of "to be" (is, are, was)

    np_acts-logits-general · gemini-2.0-flash

    is/are/was plus adjective or gerund

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    送到
    -0.58
    eradish
    -0.49
     politiche
    -0.47
     alcanzó
    -0.47
    WhereInput
    -0.45
     combusti
    -0.44
     देखा
    -0.44
     démocr
    -0.43
     preced
    -0.42
    打了
    -0.42
    POSITIVE LOGITS
     autorytatywna
    0.85
     making
    0.84
     doing
    0.82
    WebElementEntity
    0.82
    Jeografia
    0.78
     taking
    0.78
    tvguidetime
    0.78
     going
    0.77
     giving
    0.76
     responding
    0.75
    Activations Density 0.227%

    No Known Activations