© 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. 15-GEMMASCOPE-RES-16K
    11. 2139
    Prev
    Next
    INDEX
    Explanations

    items related to mechanical and electrical components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Enigma
    -0.52
    LOTTE
    -0.46
     Yuma
    -0.46
     kasarigan
    -0.46
    berkeley
    -0.45
    urably
    -0.44
    énario
    -0.44
     vali
    -0.43
    ClientSize
    -0.43
     Enterprise
    -0.43
    POSITIVE LOGITS
     AssemblyCulture
    0.47
     onOptions
    0.46
     extranjera
    0.45
     Aérea
    0.43
     étoient
    0.42
     idéia
    0.41
     Económica
    0.41
     étrang
    0.40
     paisagem
    0.40
     aérea
    0.40
    Activations Density 1.494%

    No Known Activations