© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16355
    Prev
    Next
    INDEX
    Explanations

    concepts related to separation or independence in various contexts

    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
     suro
    -0.35
     trous
    -0.32
    าท
    -0.32
     superficies
    -0.30
     poesía
    -0.29
     étapes
    -0.29
     plages
    -0.28
     veranderen
    -0.28
    FundMe
    -0.28
    mahami
    -0.28
    POSITIVE LOGITS
     separate
    1.30
    separate
    1.29
     Separate
    1.20
     separately
    1.15
    Separate
    1.14
     seperate
    1.11
     SEPAR
    1.02
     terpisah
    1.01
     separado
    1.01
    separ
    0.87
    Activations Density 0.433%

    No Known Activations