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. 6212
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities, particularly those with the prefix "De."

    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
     itſelf
    -0.94
     Efq
    -0.92
     leaſt
    -0.82
     Chriſt
    -0.80
     Houſe
    -0.80
     faſt
    -0.77
     Majefty
    -0.77
     raiſ
    -0.75
     ―――――
    -0.74
     poffible
    -0.74
    POSITIVE LOGITS
     De
    2.90
    De
    2.65
     Де
    1.21
     DeV
    1.12
     DeL
    1.01
    Де
    0.98
     DeWitt
    0.91
     Di
    0.90
     Del
    0.89
     Dever
    0.88
    Activations Density 0.081%

    No Known Activations