© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14686
    Prev
    Next
    INDEX
    Explanations

    technical terms related to web server configuration and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    GEBURTSDATUM
    -0.59
    WithIOException
    -0.51
    mybatisplus
    -0.46
     Chwiliwch
    -0.45
     leaſt
    -0.44
     deſt
    -0.43
     ſur
    -0.43
    Arbeit
    -0.43
    GIVEREF
    -0.43
     fubject
    -0.43
    POSITIVE LOGITS
    antMatchers
    0.53
     visitó
    0.46
     visitors
    0.46
     visited
    0.45
     visits
    0.45
     visit
    0.45
     besö
    0.45
     ziyaret
    0.42
     webpage
    0.41
    visit
    0.40
    Activations Density 0.323%

    No Known Activations