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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 15783
    Prev
    Next
    INDEX
    Explanations

    phrases and terminology related to artistic talent and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nonatomic
    -0.73
    nonatomic
    -0.65
    expandindo
    -0.64
    stdafx
    -0.63
    MigrationBuilder
    -0.62
    #
    -0.61
    Datuak
    -0.59
    findpost
    -0.58
    ionView
    -0.58
    存于互联网档案馆
    -0.55
    POSITIVE LOGITS
     समीक्षक
    0.57
    alyptus
    0.56
    toja
    0.55
    🤫
    0.54
    צלחה
    0.54
    wanan
    0.53
     déb
    0.53
    petito
    0.51
    verifyException
    0.50
    下载附件
    0.49
    Activations Density 4.051%

    No Known Activations