© 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. 18-GEMMASCOPE-RES-16K
    11. 2184
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational efficiency and management strategies

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

    growth or expansion

    np_acts-logits-general · gemini-2.0-flash

    growth and expansion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -};
    -0.50
     Bizarre
    -0.49
    leen
    -0.47
    }))
    -0.46
    Deep
    -0.44
     Deep
    -0.43
    DEEP
    -0.43
     Apply
    -0.42
    deep
    -0.42
    ɵɵelementEnd
    -0.42
    POSITIVE LOGITS
     growth
    2.16
    growth
    1.95
    Growth
    1.95
     expansion
    1.93
     Growth
    1.92
     GROWTH
    1.75
     Expansion
    1.72
    expansion
    1.65
    Expansion
    1.64
     growing
    1.63
    Activations Density 0.299%

    No Known Activations