© 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. 12-GEMMASCOPE-RES-16K
    11. 6687
    Prev
    Next
    INDEX
    Explanations

    numerical data and measurements, particularly in the context of scientific information and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toDouble
    -0.45
    setList
    -0.44
     feel
    -0.41
    導
    -0.41
    Ổ
    -0.40
    czaj
    -0.40
     pile
    -0.39
     szóci
    -0.39
    Jo
    -0.38
     list
    -0.38
    POSITIVE LOGITS
    ViewFeatures
    1.00
     становника
    0.94
    PerformLayout
    0.91
     GenerationType
    0.89
     ExecuteAsync
    0.88
    getMinutes
    0.87
    astéro
    0.75
    
    0.74
    ########.
    0.73
     "..\..\
    0.72
    Activations Density 1.194%

    No Known Activations