© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12474
    Prev
    Next
    INDEX
    Explanations

    elements related to programming constructs, particularly those involving conditions and loops

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

    Code with conditional statements

    np_acts-logits-general · gemini-2.0-flash

    logical operators and code structure

    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
    ']=='
    -0.77
    };*/
    -0.72
    '};
    -0.72
    });*/
    -0.70
    ]=="
    -0.70
    ']);
    
    -0.69
    "]));
    -0.68
    ]=='
    -0.67
    RefNanny
    -0.67
    })*/
    -0.67
    POSITIVE LOGITS
     &&
    1.15
     ||
    1.14
    ||
    0.89
    &&
    0.84
     thì
    0.66
     then
    0.63
     ||
    
    0.62
     allora
    0.59
     entonces
    0.56
    &&(
    0.55
    Activations Density 0.241%

    No Known Activations