© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 1799
    Prev
    Next
    INDEX
    Explanations

    phrases or words indicating fractions or proportions, particularly focusing on "half."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وتسجيلات
    -0.83
     مُعرِّف
    -0.81
    ="#"><
    -0.80
    })));
    -0.79
    بوابة
    -0.77
    ://"
    -0.76
    })*/
    -0.75
    UpInside
    -0.75
    upuncture
    -0.75
     Marlin
    -0.75
    POSITIVE LOGITS
     half
    1.88
     Half
    1.73
    Half
    1.67
    half
    1.67
     HALF
    1.67
    HALF
    1.47
     halves
    1.31
    半
    1.13
     halve
    1.00
     metade
    0.98
    Activations Density 0.036%

    No Known Activations