© 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. 9-GEMMASCOPE-RES-16K
    11. 16029
    Prev
    Next
    INDEX
    Explanations

    instances of the word "primarily" and related contexts indicating a primary focus or role

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enni
    -0.52
    tagHelper
    -0.51
     addirittura
    -0.51
     potentially
    -0.51
     dokonce
    -0.49
    Can
    -0.49
    X
    -0.48
    potentially
    -0.47
     zelfs
    -0.47
     olimp
    -0.47
    POSITIVE LOGITS
    Mostly
    1.27
     mainly
    1.25
     Mostly
    1.25
     Mainly
    1.24
     hauptsächlich
    1.21
     Primarily
    1.18
    mainly
    1.17
     primarily
    1.17
    primarily
    1.15
     mostly
    1.15
    Activations Density 0.502%

    No Known Activations