© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 4238
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives related to cleanliness or lack thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.65
    PreInfinity
    -0.56
     ſtre
    -0.55
    NameInMap
    -0.54
    исленность
    -0.53
    bukkit
    -0.53
    apimachinery
    -0.51
     dieß
    -0.51
     cauſe
    -0.50
    verhältnis
    -0.50
    POSITIVE LOGITS
     juicy
    1.45
     messy
    1.45
     smelly
    1.42
     noisy
    1.41
     dusty
    1.35
    noisy
    1.33
     muddy
    1.33
     nasty
    1.31
     bumpy
    1.31
     dirty
    1.30
    Activations Density 0.146%

    No Known Activations