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. 2833
    Prev
    Next
    INDEX
    Explanations

    phrases related to fields in inventions or patents

    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
     myſelf
    -1.17
     Cæsar
    -1.16
     Majefty
    -1.15
     Monfieur
    -1.13
     poffible
    -1.08
     themſelves
    -1.06
     himſelf
    -1.04
     pleaſure
    -1.04
     decorativas
    -1.00
     reaſon
    -0.99
    POSITIVE LOGITS
     Fields
    1.81
     fields
    1.75
     field
    1.73
     Field
    1.71
     getField
    1.62
     FIELD
    1.62
    fields
    1.56
    Fields
    1.53
    Field
    1.51
    field
    1.49
    Activations Density 0.075%

    No Known Activations