© 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. 10369
    Prev
    Next
    INDEX
    Explanations

    specific nouns and phrases that indicate time, context, and significant actions in discussions

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

    "Of" follows the activating token

    np_acts-logits-general · gemini-2.0-flash

    entirety of duration

    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
     muß
    -0.83
     mußten
    -0.68
     mußte
    -0.68
     skall
    -0.68
    faßt
    -0.67
     läßt
    -0.65
     Moslem
    -0.64
     daß
    -0.61
     wußte
    -0.58
     müßte
    -0.57
    POSITIVE LOGITS
     incentiv
    1.04
     nuanced
    1.02
     Notably
    0.93
     underwhelming
    0.92
     prioritizing
    0.90
     prioritize
    0.90
     impactful
    0.89
     prioritized
    0.84
     microbiome
    0.83
     mentorship
    0.83
    Activations Density 8.333%

    No Known Activations