© 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 - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 3525
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" and other prepositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawDesc
    -0.69
     Theſe
    -0.68
    ніципалі
    -0.66
    Personendaten
    -0.65
    ]--;
    -0.64
    ViewFeatures
    -0.59
     itſelf
    -0.58
    Glej
    -0.57
    шње
    -0.56
    Demografie
    -0.54
    POSITIVE LOGITS
     صوتيه
    0.65
    ArrowToggle
    0.61
     polícia
    0.54
    níky
    0.52
    lexia
    0.52
    SerializeField
    0.51
    发表于
    0.50
    даго
    0.50
     đế
    0.50
    anyahu
    0.49
    Activations Density 0.332%

    No Known Activations