© 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. 1086
    Prev
    Next
    INDEX
    Explanations

    references to legal claims and citizenship issues

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

    "and" followed by "another," "the," "a," or "once."

    np_acts-logits-general · gemini-2.0-flash

    one ... and another

    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
     many
    -0.60
    Many
    -0.52
     muchos
    -0.49
     muchas
    -0.48
     многие
    -0.48
     Many
    -0.47
    many
    -0.46
     et
    -0.44
    <eos>
    -0.44
    等
    -0.43
    POSITIVE LOGITS
     secondly
    1.14
    findpost
    1.07
    IndentedString
    0.99
    QMetaType
    0.97
    それと
    0.96
    IntoConstraints
    0.93
     defaultstate
    0.93
     ModelExpression
    0.91
     للاسماء
    0.90
     estekak
    0.89
    Activations Density 0.528%

    No Known Activations