© 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. 4-GEMMASCOPE-RES-16K
    11. 10832
    Prev
    Next
    INDEX
    Explanations

    phrases related to reasons and justifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.75
     виправивши
    -0.55
    AddTagHelper
    -0.54
     TestBed
    -0.52
    
    -0.51
    Clik
    -0.50
    TextWatcher
    -0.50
    principalTable
    -0.49
    )(((
    -0.47
    AdapterView
    -0.47
    POSITIVE LOGITS
    DockStyle
    0.71
    之所以
    0.66
    最快更新
    0.64
    至于
    0.64
    ệc
    0.61
    至於
    0.61
    具体
    0.61
    angol
    0.60
    PositiveButton
    0.60
     kasarigan
    0.59
    Activations Density 0.865%

    No Known Activations