© 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. 13952
    Prev
    Next
    INDEX
    Explanations

    references to different classifications or categories

    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
     gekomen
    -0.54
     táctil
    -0.54
     Komunikasi
    -0.53
    prefixer
    -0.52
     titolata
    -0.52
     financeira
    -0.51
     själ
    -0.51
     térmica
    -0.51
     sostenibilidad
    -0.50
     Hingga
    -0.50
    POSITIVE LOGITS
     type
    1.02
     kinds
    0.89
     types
    0.88
     TYPE
    0.78
     Type
    0.78
    type
    0.77
    kinds
    0.74
     tipo
    0.73
     kind
    0.72
    ntype
    0.70
    Activations Density 0.279%

    No Known Activations