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

    Neuronpedia

    Jacobian LensNEW
    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. 14-GEMMASCOPE-RES-16K
    11. 14367
    Prev
    Next
    INDEX
    Explanations

    patterns related to academic or technical formatting, such as citations and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cstdio
    -0.52
     جمله
    -0.49
     متحده
    -0.49
    Vanjske
    -0.48
     تانيه
    -0.44
    zeit
    -0.43
     satunya
    -0.43
     esterni
    -0.43
     */,
    -0.41
     lider
    -0.41
    POSITIVE LOGITS
     Мексичка
    0.89
     незавершена
    0.83
    NewUrlParser
    0.74
    AsUp
    0.71
     دیکھیے
    0.70
     mergeFrom
    0.70
     فريبيس
    0.69
    IntoConstraints
    0.69
     PropertyChanged
    0.66
     CWE
    0.66
    Activations Density 0.330%

    No Known Activations