Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7144
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal arguments and judicial decisions

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

    Discussion of an issue or topic

    np_acts-logits-general · gemini-2.0-flash

    issue, matter, point, question

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    PageContext
    -0.57
    chaub
    -0.56
    onSuccess
    -0.56
     LoggerFactory
    -0.55
    Hasil
    -0.55
    GOTREF
    -0.54
     成功
    -0.54
     Roskov
    -0.54
     provato
    -0.53
    zeichneten
    -0.53
    POSITIVE LOGITS
     issue
    2.31
     matters
    2.29
     issues
    2.26
     matter
    2.16
    issue
    1.92
    issues
    1.87
    matters
    1.85
     Issue
    1.84
     Issues
    1.83
    matter
    1.81
    Activations Density 0.719%

    No Known Activations