© 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. 11362
    Prev
    Next
    INDEX
    Explanations

    terms related to rates of change, particularly slow movements or responses

    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
    enderror
    -0.32
    disposable
    -0.31
     Kurz
    -0.31
     Sexton
    -0.30
    ợp
    -0.29
    DropTable
    -0.28
    Kurz
    -0.28
    hender
    -0.28
     intStringLen
    -0.28
    ngdoc
    -0.28
    POSITIVE LOGITS
     slow
    3.44
     Slow
    3.17
    Slow
    3.16
    slow
    3.13
     slower
    3.02
     slowest
    2.80
     SLOW
    2.77
     slowed
    2.70
     slows
    2.69
    SLOW
    2.56
    Activations Density 0.823%

    No Known Activations