© 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. 15-GEMMASCOPE-RES-16K
    11. 3342
    Prev
    Next
    INDEX
    Explanations

    terms related to adjustments and calibration processes in mechanical or electronic systems

    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
    Panamoan
    -0.61
    KURZBESCHREIBUNG
    -0.60
    vatar
    -0.59
     Италијани
    -0.57
     surla
    -0.56
     propOrder
    -0.56
     Propag
    -0.54
     pajero
    -0.53
    alsy
    -0.53
     Shovel
    -0.52
    POSITIVE LOGITS
     adjustment
    0.80
    調整
    0.79
     adjust
    0.73
     adjusting
    0.72
    adjustment
    0.71
     adjustments
    0.71
     adjusted
    0.70
     adjusts
    0.66
     調整
    0.63
     ADJUST
    0.62
    Activations Density 0.867%

    No Known Activations