© 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. 8143
    Prev
    Next
    INDEX
    Explanations

    terms related to data analysis and statistical modeling, particularly in relation to algorithms and their performance metrics

    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
     ""],
    -0.44
     korzyst
    -0.39
    AntiForgeryToken
    -0.39
    TypedDataSet
    -0.39
     ơi
    -0.38
     Utiliza
    -0.38
    PostConstruct
    -0.36
     BoxFit
    -0.35
    Portail
    -0.35
    EndContext
    -0.34
    POSITIVE LOGITS
     representing
    1.49
     represent
    1.49
     represents
    1.45
     describing
    1.35
     describes
    1.34
     describe
    1.33
     reflects
    1.30
     reflect
    1.30
     reflecting
    1.28
    representing
    1.27
    Activations Density 1.766%

    No Known Activations