© 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. 16-GEMMASCOPE-RES-16K
    11. 4960
    Prev
    Next
    INDEX
    Explanations

    references to modules and lists in a programming context

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

    after certain capital letters

    np_acts-logits-general · gemini-2.0-flash

    to JSONoneof structuresEmpty Stringraw Value

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     <<<<<<<<<<<<<<
    -1.00
    styleable
    -0.83
     mapStateToProps
    -0.73
    indd
    -0.71
     للمعارف
    -0.70
    GEBURTSDATUM
    -0.66
    setupUi
    -0.63
     Мексичка
    -0.62
    GraphicsUnit
    -0.62
     Blinds
    -0.62
    POSITIVE LOGITS
    abase
    0.46
     боль
    0.44
    ţional
    0.43
     predicated
    0.43
    ım
    0.43
    APH
    0.43
     своими
    0.42
     стране
    0.42
     deep
    0.42
    ährend
    0.42
    Activations Density 0.092%

    No Known Activations