© 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. 125182
    Prev
    Next
    INDEX
    Explanations

    words associated with sparkle and shine

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

    glitter and sparkle

    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
    ConstraintMaker
    -0.74
     gyhoeddwyd
    -0.62
     AVC
    -0.59
     indisponible
    -0.57
    styleType
    -0.57
     Nio
    -0.57
     الرياضيه
    -0.57
    Források
    -0.57
     RDC
    -0.56
    mtd
    -0.54
    POSITIVE LOGITS
     glitter
    1.98
    Glitter
    1.75
     Glitter
    1.75
    glitter
    1.68
     glit
    1.25
     Glit
    1.05
     glittering
    1.02
     sparkle
    0.97
     sparkly
    0.96
    glit
    0.96
    Activations Density 0.003%

    No Known Activations