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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10324
    Prev
    Next
    INDEX
    Explanations

    the concept of obligation or necessity in various contexts

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

    Followed by "need" or "point"

    np_acts-logits-general · gemini-2.0-flash

    no need to / no point in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unmistak
    -0.39
     appropriately
    -0.39
     correctly
    -0.37
    บ้าง
    -0.37
     successfully
    -0.36
    ViewImports
    -0.35
     quietly
    -0.34
    richTextPanel
    -0.34
     suitably
    -0.34
     einige
    -0.34
    POSITIVE LOGITS
    わざわざ
    0.83
     चीज़ों
    0.74
     unnecessary
    0.72
     unnecessarily
    0.72
     fancy
    0.69
    protoimpl
    0.68
     fuss
    0.68
     needlessly
    0.66
     inneces
    0.66
     worrying
    0.66
    Activations Density 0.522%

    No Known Activations