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. 12335
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Peter."

    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
     itſelf
    -0.94
     Monfieur
    -0.93
     myſelf
    -0.91
     iconFacebook
    -0.90
     purpoſe
    -0.88
    çalves
    -0.87
     faſt
    -0.86
    basicConfig
    -0.82
     pleaſure
    -0.81
     Majefty
    -0.81
    POSITIVE LOGITS
     Peter
    3.04
    Peter
    2.85
     PETER
    2.36
    peter
    2.18
     peter
    2.17
    PETER
    2.11
     Peters
    1.76
    彼得
    1.52
    Peters
    1.52
     Pete
    1.49
    Activations Density 0.064%

    No Known Activations