© 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. 5-GEMMASCOPE-RES-16K
    11. 62
    Prev
    Next
    INDEX
    Explanations

    technical terminology and specific naming conventions related to processes or roles in specialized fields

    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
    办法
    -0.88
    ه
    -0.87
     Guadal
    -0.87
    ed
    -0.85
     CTP
    -0.82
     Tacitus
    -0.81
     Stans
    -0.81
     Wilber
    -0.79
    帖最后由
    -0.79
    dtp
    -0.78
    POSITIVE LOGITS
    UIAlert
    0.83
    awtextra
    0.81
    pyplot
    0.80
    AnchorTagHelper
    0.79
     Hagen
    0.76
     pyplot
    0.75
     ye
    0.75
    findpost
    0.74
    ľov
    0.74
    wreck
    0.74
    Activations Density 4.795%

    No Known Activations