© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 67962
    Prev
    Next
    INDEX
    Explanations

    negative numerical values, particularly in the context of mathematical expressions or equations

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

    mathematical expressions with symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     témoig
    -0.81
    ⟬
    -0.80
     ſind
    -0.79
     ddelwed
    -0.77
     ſuo
    -0.75
     beſte
    -0.74
     Weiſe
    -0.74
    ésultats
    -0.74
    𞤭
    -0.74
    𞤫
    -0.73
    POSITIVE LOGITS
    (-
    0.86
    }=-
    0.78
    [-\
    0.75
    )=-\
    0.74
    )=-
    0.73
    =-
    0.73
    }=-\
    0.73
    [-
    0.72
     (-
    0.71
    =-\
    0.71
    Activations Density 0.419%

    No Known Activations