© 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. 24-GEMMASCOPE-RES-16K
    6. 2842
    Prev
    Next
    INDEX
    Explanations

    numerical representations or codes associated with significant statistics or identifiers

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

    Years ending in "0", "1", "4", "5", "6", "9"

    np_acts-logits-general · gemini-2.0-flash

    years starting with 18

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hObject
    -0.54
    ttps
    -0.52
    }))
    
    -0.51
    mybatisplus
    -0.50
     AssemblyCulture
    -0.48
    ]));
    
    -0.48
    }));
    
    -0.48
    \|_{\
    -0.47
     ldc
    -0.47
    /******/
    -0.46
    POSITIVE LOGITS
    RenderAtEndOf
    0.76
     веке
    0.58
    9
    0.57
    世纪
    0.57
    世紀
    0.57
    --]
    0.57
    $_['
    0.56
     "..\..\
    0.56
     noDo
    0.55
    7
    0.54
    Activations Density 0.057%

    No Known Activations