© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 13758
    Prev
    Next
    INDEX
    Explanations

    instances of change and improvement in systems or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "to" that often relate to actions

    np_acts-logits-general · gemini-2.0-flash

    implementing or adopting actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    galus
    -0.71
    IVEREF
    -0.66
     disponibilités
    -0.58
    erapeu
    -0.57
     kaarangay
    -0.55
    ArrowToggle
    -0.55
    renderItem
    -0.55
    PostExecute
    -0.55
    CloseHandle
    -0.54
    
    -0.54
    POSITIVE LOGITS
     implemented
    1.98
     implement
    1.93
     implementing
    1.91
     implementation
    1.85
    implement
    1.72
    Implementing
    1.67
     Implementing
    1.67
     Implement
    1.64
     implementa
    1.64
     adopt
    1.61
    Activations Density 0.490%

    No Known Activations