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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122886
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to celebrations and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    จึง
    -0.38
     appearing
    -0.33
     at
    -0.33
    Beijinhos
    -0.33
     existing
    -0.33
     there
    -0.33
     use
    -0.33
     cỡ
    -0.32
     Strukturen
    -0.32
     prossimo
    -0.31
    POSITIVE LOGITS
     autorytatywna
    0.79
    Geplaatst
    0.75
     tartalomajánló
    0.71
    Personendaten
    0.69
    DockStyle
    0.65
     تضيفلها
    0.65
     transfieras
    0.65
    XmlAccessType
    0.64
    ="@+
    0.63
     intStringLen
    0.63
    Activations Density 0.001%

    No Known Activations