© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 9566
    Prev
    Next
    INDEX
    Explanations

    specific mentions of names and nouns associated with characters or entities, particularly in cultural or mythological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ので
    -1.91
    able
    -1.65
    ability
    -1.47
    age
    -1.27
    ably
    -1.13
    ages
    -1.13
    away
    -1.11
    au
    -1.05
    ab
    -1.04
    ables
    -1.04
    POSITIVE LOGITS
     EconPapers
    0.40
    atteindre
    0.33
    interprétation
    0.33
    zelfde
    0.31
    存于互联网档案馆
    0.31
    gridy
    0.30
    étape
    0.30
    enfance
    0.30
    AnchorStyles
    0.29
    entraînement
    0.29
    Activations Density 1.328%

    No Known Activations