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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13044
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of mechanisms and processes

    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
     Wicidata
    -0.48
    MockMvc
    -0.46
    antMatchers
    -0.44
    ⤹
    -0.43
    itania
    -0.42
     Chwiliwch
    -0.41
     TRAN
    -0.40
     glycerol
    -0.40
    FileChooser
    -0.40
    Према
    -0.40
    POSITIVE LOGITS
     vstup
    0.41
     Wahrheit
    0.40
    postsleuth
    0.37
     Bereiche
    0.37
     îna
    0.36
     feeds
    0.36
     actualidad
    0.36
     templado
    0.36
     verás
    0.35
     húmedo
    0.35
    Activations Density 0.527%

    No Known Activations