© 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. 1-GEMMASCOPE-RES-16K
    11. 13916
    Prev
    Next
    INDEX
    Explanations

    phrases indicating instructions or directives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxDecoration
    -0.86
    setupUi
    -0.66
    
    -0.65
    Espèce
    -0.64
     MessageBoxIcon
    -0.63
    GEBURTSDATUM
    -0.61
    interopRequire
    -0.59
    CancelButton
    -0.59
     يتيمه
    -0.58
    BufferException
    -0.58
    POSITIVE LOGITS
     Do
    1.92
    Do
    1.67
     До
    0.89
     Lo
    0.73
     Are
    0.73
    DoNot
    0.72
     Dos
    0.72
     Go
    0.72
     Does
    0.70
     DO
    0.69
    Activations Density 0.114%

    No Known Activations