© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15163
    Prev
    Next
    INDEX
    Explanations

    calls to action or instructions for implementation

    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
     caufe
    -0.54
    hitheatre
    -0.51
     pleaſure
    -0.50
     raiſ
    -0.50
     Können
    -0.49
    ścioła
    -0.48
    restre
    -0.48
     insuffisamment
    -0.47
     LIABLE
    -0.47
    ollectionView
    -0.47
    POSITIVE LOGITS
     AssemblyCulture
    0.85
    Personendaten
    0.67
    __':
    0.61
    wpi
    0.61
    DebuggerNonUser
    0.60
    ScopeManager
    0.60
    之所以
    0.59
     EconPapers
    0.59
    paravant
    0.59
    脚注の使い方
    0.57
    Activations Density 0.263%

    No Known Activations