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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 300
    Prev
    Next
    INDEX
    Explanations

    phrases focused on ensuring and guaranteeing well-being or proper handling of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.60
     ModelExpression
    -0.60
     utafitiHapana
    -0.59
    awtextra
    -0.57
     الرياضيه
    -0.55
    httphttps
    -0.54
    Хьажоргаш
    -0.54
    RegistryLite
    -0.52
     AssemblyTitle
    -0.50
    }}],
    -0.50
    POSITIVE LOGITS
     ensure
    0.66
     proper
    0.62
    Ensure
    0.60
     pastikan
    0.56
     Ensure
    0.54
     properly
    0.54
    Proper
    0.52
    proper
    0.51
     correct
    0.50
     correcto
    0.50
    Activations Density 0.245%

    No Known Activations