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. 7-GEMMASCOPE-RES-16K
    6. 9392
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships or connections between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.97
    DockStyle
    -0.96
     DNI
    -0.90
     Prisons
    -0.88
     تضيفلها
    -0.88
    dymyr
    -0.87
     سكانية
    -0.87
     swe
    -0.85
     sceptre
    -0.84
    RegressionTest
    -0.83
    POSITIVE LOGITS
     related
    1.99
    related
    1.95
    Related
    1.88
     Related
    1.74
     RELATED
    1.54
    RELATED
    1.50
     relating
    1.32
     relates
    1.32
     relate
    1.24
     unrelated
    1.18
    Activations Density 0.122%

    No Known Activations