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. 7747
    Prev
    Next
    INDEX
    Explanations

    references to the concept of diversity and the Bell inequality in various contexts

    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
    pr
    -0.58
     Prid
    -0.51
    py
    -0.50
    PR
    -0.50
    without
    -0.49
     without
    -0.49
     embalaje
    -0.48
    gov
    -0.48
    cej
    -0.47
     ufficiali
    -0.47
    POSITIVE LOGITS
    rungsseite
    0.91
     doInBackground
    0.86
     myſelf
    0.82
    RegistryLite
    0.80
     diversity
    0.80
     estimés
    0.79
    oredCriteria
    0.78
     <",
    0.78
    #+#
    0.78
     utafitiHapana
    0.76
    Activations Density 0.200%

    No Known Activations