© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 10980
    Prev
    Next
    INDEX
    Explanations

    discussions about the removal of certain entities or items, especially in legal or procedural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tableFuture
    -0.57
    Искәрмәләр
    -0.51
    EndInit
    -0.50
     propOrder
    -0.49
     uLocal
    -0.49
    ARROLL
    -0.45
     cherchés
    -0.45
    AxisAlignment
    -0.44
     AspNetCore
    -0.44
     Buk
    -0.44
    POSITIVE LOGITS
     Remove
    0.77
     remove
    0.73
    Remove
    0.72
     Removes
    0.72
    remove
    0.72
     Removing
    0.70
     removed
    0.69
    Removing
    0.69
     Removed
    0.67
    Removes
    0.67
    Activations Density 0.236%

    No Known Activations