© 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. 14-GEMMASCOPE-RES-16K
    11. 5665
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rare" and related terms indicating rarity or unusual occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.77
    IntoConstraints
    -0.58
    MigrationBuilder
    -0.57
     EconPapers
    -0.56
     viewDidLoad
    -0.56
    namic
    -0.54
    StoryboardSegue
    -0.54
    Personendaten
    -0.52
    SceneManagement
    -0.50
     ginge
    -0.49
    POSITIVE LOGITS
     rare
    1.43
    Rare
    1.21
     Rare
    1.21
     rarer
    1.14
     rarity
    1.11
    rare
    1.09
     RARE
    1.06
     rarest
    1.02
     rares
    1.01
     selten
    1.00
    Activations Density 0.155%

    No Known Activations