© 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. 33-GEMMASCOPE-RES-16K
    11. 448
    Prev
    Next
    INDEX
    Explanations

    structural elements of data descriptions and fields related to programming documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.88
     ModelExpression
    -0.75
    AddTagHelper
    -0.65
    хьтан
    -0.64
     Савезне
    -0.63
     disambiguazione
    -0.59
     AssemblyCulture
    -0.59
    RTEE
    -0.56
    GEBURTS
    -0.55
     Biôgrafia
    -0.54
    POSITIVE LOGITS
     étoient
    0.49
     avoient
    0.47
     Sünde
    0.46
     feroit
    0.45
     säll
    0.45
     chrétiens
    0.43
     étoit
    0.43
     tagħ
    0.42
     Allgemeinen
    0.41
    Források
    0.40
    Activations Density 0.067%

    No Known Activations