© 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. 20-GEMMASCOPE-RES-16K
    6. 10617
    Prev
    Next
    INDEX
    Explanations

    elements that indicate decision-making or conditional logic

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

    Comes before mathematical symbols or formulas

    np_acts-logits-general · gemini-2.0-flash

    multilingual academic and technical content

    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
     виправивши
    -0.71
    Demografia
    -0.69
     <>",
    -0.69
    Попис
    -0.63
    ]').
    -0.60
    }}^
    -0.60
     '',
    
    -0.59
     pungkas
    -0.59
     "");
    
    -0.59
    "],
    
    -0.58
    POSITIVE LOGITS
    saraba
    0.66
    гава
    0.62
    Portail
    0.59
     dessinée
    0.57
    下载附件
    0.56
     dunque
    0.50
    Hozzáférés
    0.50
     Alors
    0.50
     Portail
    0.49
     Então
    0.48
    Activations Density 0.054%

    No Known Activations