© 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. 0-GEMMASCOPE-RES-16K
    11. 9539
    Prev
    Next
    INDEX
    Explanations

    specific names and terms from various contexts such as movies, places, and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.58
     EconPapers
    -0.48
     Réponses
    -0.42
     незавершена
    -0.41
     Signalez
    -0.39
     referenties
    -0.39
     tæ
    -0.39
    MergeFrom
    -0.38
    complexType
    -0.38
    thig
    -0.36
    POSITIVE LOGITS
    tvguidetime
    0.55
     desnuda
    0.52
    navigationItem
    0.52
     Shorts
    0.48
    iPod
    0.48
    Shorts
    0.48
     glú
    0.48
    aarrggbb
    0.48
    visor
    0.48
     iphone
    0.48
    Activations Density 2.020%

    No Known Activations