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. 21-GEMMASCOPE-RES-16K
    6. 813
    Prev
    Next
    INDEX
    Explanations

    elements and characteristics related to local amenities and attractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.58
    MethodManager
    -0.55
     circonstances
    -0.53
    ClientSize
    -0.53
    offsetof
    -0.53
     partenariat
    -0.49
     comportements
    -0.47
    opress
    -0.47
    protoimpl
    -0.47
    Jeografia
    -0.47
    POSITIVE LOGITS
     attractions
    1.16
     shops
    1.11
     restaurants
    1.08
     entertainment
    0.99
     eateries
    0.99
     shopping
    0.94
     museums
    0.94
     cultural
    0.92
     nightlife
    0.87
     amenities
    0.86
    Activations Density 0.110%

    No Known Activations