© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 2020
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical values or mathematical functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iſt
    -1.25
     houſe
    -1.23
     myſelf
    -1.21
     ―――――
    -1.19
     themſelves
    -1.17
     ་་
    -1.16
     $_"
    -1.16
     Anſ
    -1.15
     ſind
    -1.15
     Houſe
    -1.13
    POSITIVE LOGITS
    n
    2.90
     n
    2.18
    N
    1.96
     N
    1.56
    setN
    1.27
    getN
    1.24
    ｎ
    1.20
    nn
    1.15
    𝗻
    1.14
    н
    1.01
    Activations Density 0.251%

    No Known Activations