© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 8534
    Prev
    Next
    INDEX
    Explanations

    programming concepts and structures, particularly in relation to coding in JavaScript and other languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enggak
    -0.58
     somebody
    -0.57
     stuff
    -0.54
     noires
    -0.53
     everybody
    -0.51
    people
    -0.51
     Leute
    -0.51
     problème
    -0.49
    stuff
    -0.49
     maybe
    -0.49
    POSITIVE LOGITS
    เพื่อ
    1.20
     mediante
    1.20
     oleh
    1.14
     sebagai
    1.09
     poprzez
    1.08
     nhằm
    1.08
     afin
    1.07
     для
    1.05
     tại
    1.05
     mientras
    1.02
    Activations Density 1.012%

    No Known Activations