Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 14847
    Prev
    Next
    INDEX
    Explanations

    adverbs and their variations ending in 'ly'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endregion
    -0.70
    gameserver
    -0.64
    WebControls
    -0.64
     vertebra
    -0.64
    marcos
    -0.63
    reactstrap
    -0.61
     createState
    -0.61
    glLoadIdentity
    -0.61
    Życiorys
    -0.61
    illoma
    -0.60
    POSITIVE LOGITS
    ly
    3.75
    LY
    2.92
    ely
    1.57
    ELY
    1.57
     ly
    1.49
    ingly
    1.47
    lyt
    1.46
    mente
    1.46
    lys
    1.43
    dly
    1.38
    Activations Density 0.045%

    No Known Activations