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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 8108
    Prev
    Next
    INDEX
    Explanations

    phrases that relate to the quality of atmosphere in social or professional settings

    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
     «
    -0.58
    bür
    -0.55
    winston
    -0.55
    «
    -0.51
    一套
    -0.49
    に興味
    -0.48
    azer
    -0.48
    قد
    -0.48
     MainAxisSize
    -0.48
    <h2>
    -0.48
    POSITIVE LOGITS
     atmosphere
    1.03
     nahilalakip
    0.90
    atmosphere
    0.83
     blest
    0.77
     ambience
    0.76
    tôi
    0.76
     ambiance
    0.74
     Monfieur
    0.72
    mặt
    0.70
    HasAnnotation
    0.69
    Activations Density 0.130%

    No Known Activations