© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 8842
    Prev
    Next
    INDEX
    Explanations

    comparisons or phrases indicating improvement or enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.80
    URLException
    -0.78
    cifix
    -0.78
    Zeneca
    -0.78
    SequentialGroup
    -0.77
    Linki
    -0.76
    origen
    -0.73
    حوالہ
    -0.72
    UpInside
    -0.72
    geology
    -0.71
    POSITIVE LOGITS
     better
    2.12
    better
    2.07
    Better
    1.94
     Better
    1.93
     BETTER
    1.89
     mejor
    1.43
     melhor
    1.41
     mieux
    1.35
     beter
    1.34
     bedre
    1.31
    Activations Density 0.070%

    No Known Activations