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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14-GEMMASCOPE-RES-16K
    6. 4185
    Prev
    Next
    INDEX
    Explanations

    issues related to procedural or systemic inefficiencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.66
     utafitiHapana
    -0.60
     defaultstate
    -0.49
    badah
    -0.47
    ApiProperty
    -0.46
    PHPExcel
    -0.44
    arsa
    -0.43
     wir
    -0.41
     Jansen
    -0.41
    casa
    -0.41
    POSITIVE LOGITS
    SequentialGroup
    0.78
     initComponents
    0.68
     nemlig
    0.65
     whereby
    0.65
    下载附件
    0.59
    TintMode
    0.59
     récomp
    0.59
    Viitteet
    0.59
     Insee
    0.58
     correctes
    0.57
    Activations Density 0.750%

    No Known Activations