© 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. 8956
    Prev
    Next
    INDEX
    Explanations

    references to scientific or technical notation, particularly those involving parentheses

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

    Tokens that come before "s" often in parentheses

    np_acts-logits-general · gemini-2.0-flash

    parent(s)/guardian(s)

    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
    CloseOperation
    -0.73
     onCreateView
    -0.71
    }{*}{
    -0.65
    )){
    
    -0.65
    ']],
    -0.62
    "]]
    -0.60
    																	
    -0.59
    ]})
    -0.59
    ]},
    -0.58
    ]);
    
    -0.58
    POSITIVE LOGITS
    Opens
    0.91
    Rujuakan
    0.81
    ?).
    0.77
    expandindo
    0.75
     للمعارف
    0.74
    ?),
    0.73
    link
    0.72
    €)
    0.72
     lenker
    0.66
    middels
    0.66
    Activations Density 0.313%

    No Known Activations