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. 18-GEMMASCOPE-RES-16K
    6. 10161
    Prev
    Next
    INDEX
    Explanations

    promotional activities related to crowdfunding campaigns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.74
    tvguidetime
    -0.58
     towed
    -0.58
    ској
    -0.56
     obligé
    -0.55
     âgé
    -0.54
    ếm
    -0.53
     Radiator
    -0.53
    mazioni
    -0.52
    ânico
    -0.52
    POSITIVE LOGITS
     Black
    0.84
     Kickstarter
    0.77
    Black
    0.76
     Cyber
    0.70
     preorder
    0.69
     black
    0.68
    black
    0.66
     BLACK
    0.66
    BLACK
    0.66
     early
    0.64
    Activations Density 0.070%

    No Known Activations