© 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. 14280
    Prev
    Next
    INDEX
    Explanations

    references to benefits and advantages in relation to various topics

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

    "benefit" or "benefits"

    np_acts-logits-general · gemini-2.0-flash

    benefit

    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
    itinéraire
    -0.57
    .*")]
    -0.57
     vengeance
    -0.55
    expandindo
    -0.52
     judiciaire
    -0.50
    
    -0.49
    SafeMath
    -0.49
    MultipartFile
    -0.48
    TabStop
    -0.47
     UITableView
    -0.47
    POSITIVE LOGITS
     benefits
    0.95
     Benefits
    0.89
     BENEFITS
    0.85
    Benefits
    0.83
     accruing
    0.79
    BENEFITS
    0.79
     benefit
    0.78
    benefits
    0.76
     accrue
    0.75
     accrued
    0.75
    Activations Density 0.141%

    No Known Activations