Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15907
    Prev
    Next
    INDEX
    Explanations

    phrases related to engaging in activities and recreational pursuits

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

    leisure activities

    np_acts-logits-general · gemini-2.0-flash

    activities, leisure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.49
    ]")]
    -0.44
    脚注の使い方
    -0.41
     présidenti
    -0.41
    GraphicsUnit
    -0.39
     المعيارى
    -0.37
     AssemblyCompany
    -0.36
     gouvernements
    -0.36
    vorschaubild
    -0.35
    AndEndTag
    -0.35
    POSITIVE LOGITS
     activities
    2.27
    activities
    1.99
     Activities
    1.98
    Activities
    1.96
     ACTIVITIES
    1.79
     activités
    1.76
     activity
    1.74
     actividades
    1.72
     Aktivitäten
    1.61
     activiteiten
    1.61
    Activations Density 0.231%

    No Known Activations