© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5903
    Prev
    Next
    INDEX
    Explanations

    legal terms and processes related to court cases

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

    Followed by a verb in past participle form

    np_acts-logits-general · gemini-2.0-flash

    followed by reason or circumstance

    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
     the
    -0.71
    <bos>
    -0.70
     rând
    -0.55
    The
    -0.54
     nämlich
    -0.46
     namelijk
    -0.45
     pă
    -0.45
    /*!
    -0.45
     The
    -0.43
     quelli
    -0.43
    POSITIVE LOGITS
     same
    1.09
     largest
    0.95
     biggest
    0.93
     slightest
    0.86
    biggest
    0.86
     tartalomajánló
    0.83
     toughest
    0.83
     longest
    0.83
     smallest
    0.82
    …~
    0.81
    Activations Density 0.802%

    No Known Activations