© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 12880
    Prev
    Next
    INDEX
    Explanations

    phrases that contain the word "of" to indicate relationships or associations in narratives

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

    story context

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Sublime
    -0.50
     Sanity
    -0.48
     gyhoeddwyd
    -0.48
     Mop
    -0.48
     rhetor
    -0.47
     baguette
    -0.47
    openhauer
    -0.46
    Rant
    -0.46
     dragonfly
    -0.46
     conserv
    -0.45
    POSITIVE LOGITS
     STORY
    0.77
     Story
    0.75
     story
    0.74
     história
    0.73
     قصة
    0.68
    STORY
    0.68
     kisah
    0.66
    Story
    0.63
     histoires
    0.62
     História
    0.61
    Activations Density 0.009%

    No Known Activations