© 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. 10-GEMMASCOPE-RES-16K
    11. 15906
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the establishment or founding of concepts, systems, or entities

    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
     Mice
    -0.72
     dream
    -0.71
    odils
    -0.65
    fcntl
    -0.65
     Peter
    -0.65
     
    -0.64
     Dream
    -0.62
     coils
    -0.61
    y
    -0.60
    갖
    -0.59
    POSITIVE LOGITS
    Establish
    1.39
     Establishment
    1.39
     establishment
    1.38
     Establish
    1.38
     Efq
    1.35
     Estab
    1.34
    Establishment
    1.33
     myſelf
    1.32
    establish
    1.29
     themſelves
    1.29
    Activations Density 0.073%

    No Known Activations