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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30835
    Prev
    Next
    INDEX
    Explanations

    references to context or contextual information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uſed
    -0.93
    SBATCH
    -0.93
     Shakspeare
    -0.91
    İstinadlar
    -0.89
     otomatig
    -0.88
     Efq
    -0.88
    ربای
    -0.82
     Monfieur
    -0.82
     Diſ
    -0.81
     ſon
    -0.80
    POSITIVE LOGITS
     context
    1.19
     contexts
    1.16
    context
    1.02
     CONTEXT
    0.95
    Context
    0.94
     Context
    0.93
    contexts
    0.88
    CONTEXT
    0.85
    Contexts
    0.84
     useContext
    0.82
    Activations Density 0.015%

    No Known Activations