© 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. 5-GEMMASCOPE-RES-16K
    11. 15032
    Prev
    Next
    INDEX
    Explanations

    CSS properties and values related to display settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zusch
    -0.48
     einzu
    -0.46
     milhares
    -0.44
     коса
    -0.44
    րան
    -0.43
     bornes
    -0.43
     cercando
    -0.43
     sonno
    -0.42
     are
    -0.42
    ղ
    -0.42
    POSITIVE LOGITS
    none
    1.20
    webElementXpaths
    1.20
    GOTREF
    1.01
     GenerationType
    0.94
    DropColumn
    0.89
    mergeFrom
    0.88
    IntoConstraints
    0.87
     EnglishChoose
    0.85
    PerformLayout
    0.85
    EndInit
    0.85
    Activations Density 0.065%

    No Known Activations