© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 5364
    Prev
    Next
    INDEX
    Explanations

    technical terms related to pulsations and flow in scientific contexts

    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
     CH
    -0.89
    CH
    -0.88
     Lach
    -0.82
     nh
    -0.82
     Uch
    -0.80
     Nash
    -0.80
    lach
    -0.79
     NASH
    -0.78
    GH
    -0.78
    woosh
    -0.77
    POSITIVE LOGITS
     myſelf
    1.06
     Efq
    1.02
     faſt
    0.97
     becauſe
    0.96
     Conſ
    0.94
     juſt
    0.93
     raiſ
    0.90
     itſelf
    0.87
     Diſ
    0.87
     poffible
    0.87
    Activations Density 1.665%

    No Known Activations