© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 10169
    Prev
    Next
    INDEX
    Explanations

    terms related to specificity and precision in descriptions or results

    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
    Portale
    -0.81
     Patro
    -0.72
     coals
    -0.70
    Mou
    -0.68
     serpent
    -0.66
    üyü
    -0.66
    onaise
    -0.64
     Bila
    -0.63
     crocodiles
    -0.63
     Gree
    -0.63
    POSITIVE LOGITS
     specific
    1.27
     SPECIFIC
    1.21
     Specific
    1.18
    specific
    1.13
    pecific
    1.10
    Specific
    1.08
    SPECIFIC
    1.05
     spesifik
    1.03
     particular
    1.02
     specifically
    1.00
    Activations Density 0.117%

    No Known Activations