Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1437
    Prev
    Next
    INDEX
    Explanations

    references to art and key concepts related to artistic practices

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

    keyboards, maps, or file structures

    np_acts-logits-general · gemini-2.0-flash

    key points, map locations, fan groups, bar graphs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "])
    
    -1.02
    "):
    
    -0.96
    '])){
    
    -0.92
    ]),
    
    -0.91
    ']))
    
    -0.91
    ")));
    
    -0.90
    ]]
    
    -0.89
    "],
    
    -0.88
    FTFY
    -0.87
    "]
    
    -0.84
    POSITIVE LOGITS
    back
    0.80
    out
    0.74
    meta
    0.73
     pleaſure
    0.73
    G
    0.72
     ſever
    0.72
    head
    0.71
     ſche
    0.70
    var
    0.70
     Diſ
    0.70
    Activations Density 0.663%

    No Known Activations