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. 3-GEMMASCOPE-RES-16K
    6. 12918
    Prev
    Next
    INDEX
    Explanations

    phrases related to dressing up and costumes

    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
    makeConstraints
    -0.57
    IVEREF
    -0.57
    rzost
    -0.55
    onoi
    -0.53
     onResponse
    -0.52
    immutable
    -0.51
    SQLException
    -0.51
    ніципалі
    -0.51
    Unsubscribe
    -0.50
     Kante
    -0.50
    POSITIVE LOGITS
     disguise
    1.29
     masquerade
    1.24
     disguised
    1.19
     masquer
    1.17
     disgu
    1.07
     disfraz
    1.03
     disfraces
    0.96
     cosplay
    0.93
     costume
    0.90
    querade
    0.90
    Activations Density 0.467%

    No Known Activations