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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14008
    Prev
    Next
    INDEX
    Explanations

    comparative phrases contrasting different entities or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsContent
    -0.66
    WireFormatLite
    -0.59
    brainly
    -0.56
     unspecified
    -0.54
     propOrder
    -0.52
    StructEnd
    -0.52
     additional
    -0.52
     vocals
    -0.52
    IBAction
    -0.52
    ientôt
    -0.51
    POSITIVE LOGITS
     meisten
    1.43
     plupart
    1.35
     kebanyakan
    1.33
     most
    1.31
     meeste
    1.30
     большин
    1.29
     many
    1.27
     большинство
    1.25
     maioria
    1.22
    大多数
    1.17
    Activations Density 0.812%

    No Known Activations