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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1511
    Prev
    Next
    INDEX
    Explanations

    terms related to finality and completion

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

    "final"

    np_acts-logits-general · gemini-2.0-flash

    final outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     bershka
    -0.61
     RTE
    -0.60
    Rodney
    -0.57
    contentValues
    -0.56
     Spreadsheet
    -0.54
    그는
    -0.54
     للمعارف
    -0.54
    jeune
    -0.54
    kko
    -0.54
     mosquito
    -0.54
    POSITIVE LOGITS
    Final
    0.94
    final
    0.91
     Final
    0.89
     FINAL
    0.88
     final
    0.88
    FINAL
    0.83
    finalize
    0.71
    Finalize
    0.63
    Finale
    0.62
     Finale
    0.60
    Activations Density 0.085%

    No Known Activations