© 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. 25-GEMMASCOPE-RES-16K
    11. 712
    Prev
    Next
    INDEX
    Explanations

    questions related to technical queries or troubleshooting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADVERTISEMENT
    -0.64
    はじめに
    -0.59
     Ceramby
    -0.57
    better
    -0.56
    sidemargin
    -0.55
     better
    -0.54
     Better
    -0.53
    Partial
    -0.53
    Referanser
    -0.53
    Better
    -0.53
    POSITIVE LOGITS
     resourceCulture
    0.61
    Demografía
    0.60
    czaj
    0.53
    出版年
    0.52
    wirk
    0.49
    west
    0.47
    wik
    0.46
    ashqai
    0.44
    wert
    0.44
    werty
    0.43
    Activations Density 0.238%

    No Known Activations