© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6003
    Prev
    Next
    INDEX
    Explanations

    conditional phrases indicating optionality or necessity

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

    Optionality; words indicating something is optional

    np_acts-logits-general · gemini-2.0-flash

    optional or necessary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يكب
    -0.52
     autorytatywna
    -0.52
    Autoritní
    -0.48
     propOrder
    -0.43
    исленность
    -0.42
    艋
    -0.42
     CGRectMake
    -0.39
     uska
    -0.38
     تانيه
    -0.38
    astéro
    -0.38
    POSITIVE LOGITS
     évent
    0.81
    omitempty
    0.71
     eventuell
    0.68
     případ
    0.66
     eventuali
    0.65
    Optional
    0.64
     ggf
    0.64
     evtl
    0.61
     possibly
    0.60
    optional
    0.60
    Activations Density 0.528%

    No Known Activations