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. 20-GEMMASCOPE-RES-16K
    6. 12956
    Prev
    Next
    INDEX
    Explanations

    gerunds and verbs indicating actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    下载附件
    -0.69
    sidemargin
    -0.67
    Portail
    -0.65
    
    -0.60
    rungsseite
    -0.60
    новништво
    -0.59
     textStatus
    -0.57
    httphttps
    -0.57
    audiovisuel
    -0.57
    netje
    -0.57
    POSITIVE LOGITS
     tartalomajánló
    0.54
    からお
    0.47
    ছ
    0.46
    以来
    0.46
    ছে
    0.44
     Дата
    0.42
     setOpen
    0.41
    PerformLayout
    0.41
    addContainerGap
    0.41
    こそ
    0.40
    Activations Density 0.071%

    No Known Activations