© 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. 6024
    Prev
    Next
    INDEX
    Explanations

    common themes or shared characteristics among different contexts or subjects

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

    "Common" or "shared" appearing in text

    np_acts-logits-general · gemini-2.0-flash

    things in common

    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
     CascadeType
    -0.66
    EndInit
    -0.58
     Exacts
    -0.56
    出版年
    -0.56
    Източници
    -0.52
    rrggbb
    -0.52
    tação
    -0.52
    ScopeManager
    -0.51
    expandindo
    -0.51
    PHONY
    -0.49
    POSITIVE LOGITS
     common
    2.41
    common
    2.04
     Common
    1.98
    Common
    1.91
     COMMON
    1.77
    COMMON
    1.62
     común
    1.61
     shared
    1.56
    共通
    1.51
     comunes
    1.48
    Activations Density 0.403%

    No Known Activations