© 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. 12968
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data analysis and statistical evaluation

    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
     propOrder
    -0.94
    TagMode
    -0.66
    Chham
    -0.64
     jsPsych
    -0.60
    ifolium
    -0.60
    IUrlHelper
    -0.59
     Extragalactic
    -0.56
    EndGlobalSection
    -0.55
    [])
    -0.54
    ]!='
    -0.52
    POSITIVE LOGITS
     itself
    0.66
     الدولى
    0.62
     themselves
    0.56
     pula
    0.56
    脚注の使い方
    0.55
    StructEnd
    0.54
    ніципа
    0.52
    น์
    0.52
     Itself
    0.52
     stessa
    0.51
    Activations Density 9.298%

    No Known Activations