© 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. 20-GEMMASCOPE-RES-16K
    11. 6179
    Prev
    Next
    INDEX
    Explanations

    segments related to system networking and secure communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming or technical code-related terms and syntax.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
     Sünde
    -0.33
    izzati
    -0.31
     herido
    -0.31
    aronder
    -0.31
     écrite
    -0.30
     especializados
    -0.30
    ngths
    -0.29
     recortes
    -0.29
     malade
    -0.28
     decorativa
    -0.28
    POSITIVE LOGITS
     Blockchain
    0.57
    bcryptjs
    0.57
     Bitcoin
    0.56
     estekak
    0.54
     dAtA
    0.53
     blockchain
    0.52
     चीज़ों
    0.52
    Geplaatst
    0.52
     Satoshi
    0.52
    OGND
    0.52
    Activations Density 0.072%

    No Known Activations