© 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. 15-GEMMASCOPE-RES-16K
    6. 5302
    Prev
    Next
    INDEX
    Explanations

    terms related to measurement and analysis methods in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AspNetCore
    -0.63
    "]];
    -0.54
    )$/,
    -0.50
    setAccessible
    -0.50
    ]};
    -0.48
    ']))
    
    -0.47
    "]);
    
    -0.47
    CodedInputStream
    -0.46
    ']);
    
    -0.45
    )))));
    -0.45
    POSITIVE LOGITS
     or
    2.67
     или
    2.17
     hoặc
    1.99
     eller
    1.98
     atau
    1.95
    或
    1.92
     oder
    1.86
     либо
    1.82
     یا
    1.80
     alebo
    1.80
    Activations Density 1.274%

    No Known Activations