Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105073
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "ngx," likely related to a software or system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     camicia
    -0.30
     post
    -0.29
     helpful
    -0.26
     chal
    -0.26
     paternal
    -0.26
     vesel
    -0.26
     Chal
    -0.25
     res
    -0.25
     policy
    -0.24
     下午
    -0.24
    POSITIVE LOGITS
    gdx
    5.63
    Gdx
    1.60
    Xna
    1.34
    reactstrap
    0.90
    mybatisplus
    0.84
     disambiguazione
    0.81
    badlogic
    0.80
     kasarigan
    0.79
    twimg
    0.78
    StoryboardSegue
    0.77
    Activations Density 0.000%

    No Known Activations