© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8135
    Prev
    Next
    INDEX
    Explanations

    sections related to coding or programming syntax and structures

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

    Numbers or digits

    np_acts-logits-general · gemini-2.0-flash

    numbers and symbols

    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
    saraba
    -0.66
    efficient
    -0.65
     Quintet
    -0.65
    fficient
    -0.64
     EFFICIENCY
    -0.61
    Elton
    -0.60
     contextLoads
    -0.59
     lolita
    -0.59
     Elton
    -0.58
    itola
    -0.58
    POSITIVE LOGITS
                            
    0.98
                             
    0.67
    						
    0.65
    3
    0.63
            
    0.61
    ../
    0.59
                           
    0.58
    ٣
    0.55
    4
    0.54
                              
    0.52
    Activations Density 0.031%

    No Known Activations