© 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. 7830
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate requirements or conditions involving minimum specifications

    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
     SwiftUI
    -0.42
    trop
    -0.38
     avond
    -0.37
    upol
    -0.36
    anton
    -0.36
    river
    -0.35
    errHandler
    -0.35
    localctx
    -0.35
    iter
    -0.35
    nelli
    -0.34
    POSITIVE LOGITS
     least
    1.13
     leaſt
    1.02
    Least
    0.90
    least
    0.88
     atleast
    0.85
     LEAST
    0.83
     Least
    0.79
     almeno
    0.79
     mindestens
    0.77
     минимум
    0.75
    Activations Density 0.432%

    No Known Activations