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. 9-GEMMASCOPE-RES-16K
    6. 15316
    Prev
    Next
    INDEX
    Explanations

    expressions related to duration and time measurements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.66
    RTEX
    -0.66
    richTextPanel
    -0.59
    bedingt
    -0.58
    lapsingToolbar
    -0.57
    qvarna
    -0.56
     CreateTagHelper
    -0.56
    INSEE
    -0.55
     ivelany
    -0.54
     consultato
    -0.54
    POSITIVE LOGITS
     Durée
    0.71
     TimeSpan
    0.66
     doInBackground
    0.63
     snippetHide
    0.58
    商品説明
    0.57
     duration
    0.56
    TimeUnit
    0.56
    TimeSpan
    0.56
    Durée
    0.55
    TextWatcher
    0.54
    Activations Density 0.255%

    No Known Activations