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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 13045
    Prev
    Next
    INDEX
    Explanations

    terms related to production and manufacturing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.78
     chakras
    -0.76
     Grimal
    -0.74
     HIPAA
    -0.72
     متعلقه
    -0.70
    valently
    -0.70
    fhir
    -0.69
     Olms
    -0.68
    AxisAlignment
    -0.68
     Worms
    -0.67
    POSITIVE LOGITS
     produc
    1.28
     produce
    1.25
     produced
    1.22
     PRODUC
    1.22
     productions
    1.19
    produce
    1.17
     produces
    1.17
     production
    1.16
     produ
    1.15
    produced
    1.15
    Activations Density 0.077%

    No Known Activations