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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 6368
    Prev
    Next
    INDEX
    Explanations

    names, particularly the name "Bob."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.43
     myſelf
    -1.33
     Majefty
    -1.31
     itſelf
    -1.26
     iſt
    -1.23
     Wikimedijinoj
    -1.23
     ་་
    -1.21
    ſelf
    -1.20
     Houſe
    -1.15
     photolibrary
    -1.14
    POSITIVE LOGITS
     Kh
    1.05
    kh
    1.01
    Kh
    1.00
     Bob
    0.81
     
    0.74
     kh
    0.74
    Bob
    0.70
     Wright
    0.67
     Z
    0.67
    er
    0.66
    Activations Density 0.096%

    No Known Activations