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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16041
    Prev
    Next
    INDEX
    Explanations

    references to specific programming packages and libraries

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Commencez
    -0.52
    期刊论文
    -0.50
    𝟹
    -0.48
     åren
    -0.46
     anledning
    -0.46
    olism
    -0.45
     början
    -0.44
    NewReader
    -0.43
     gustaMe
    -0.43
    WebControls
    -0.43
    POSITIVE LOGITS
     للاسماء
    0.56
    ViewFeatures
    0.51
    GEBURTS
    0.44
    WriteTagHelper
    0.43
    OGND
    0.42
    
    0.41
     Chwiliwch
    0.40
    spyOn
    0.40
     đích
    0.38
    httphttps
    0.38
    Activations Density 0.056%

    No Known Activations