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. 5-GEMMASCOPE-RES-16K
    6. 4018
    Prev
    Next
    INDEX
    Explanations

    phrases indicating percentages or proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    انجليز
    -0.84
     InputDecoration
    -0.74
    glades
    -0.72
     Orrell
    -0.72
    ähkö
    -0.71
     الحره
    -0.70
    PreferredItem
    -0.70
     Andree
    -0.69
    "]="
    -0.67
    }*/
    
    -0.67
    POSITIVE LOGITS
     ExecuteAsync
    0.71
     flesta
    0.61
     את
    0.59
     Drittel
    0.58
     all
    0.57
     část
    0.57
     každé
    0.57
    <bos>
    0.57
    GroupLayout
    0.57
     Prozent
    0.56
    Activations Density 0.145%

    No Known Activations