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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 10750
    Prev
    Next
    INDEX
    Explanations

    concepts related to data extraction and processing in software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issauga
    -0.88
    التالي
    -0.83
    ibatis
    -0.81
     scheda
    -0.79
    AnchorStyles
    -0.78
    lgari
    -0.78
    ymce
    -0.77
    valently
    -0.76
     Wikispecies
    -0.75
    urnum
    -0.75
    POSITIVE LOGITS
    ization
    1.22
    ation
    1.17
    cination
    1.13
    fication
    1.05
    ration
    1.04
    ally
    0.98
    stration
    0.98
    iration
    0.98
    ATION
    0.96
    vation
    0.95
    Activations Density 1.748%

    No Known Activations