© 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. 15-GEMMASCOPE-RES-16K
    11. 3198
    Prev
    Next
    INDEX
    Explanations

    expressions related to capability and capacity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     astore
    -0.42
    FileNotFound
    -0.36
     sandalias
    -0.36
     söyle
    -0.35
    throwaway
    -0.35
     agresión
    -0.35
     embarazada
    -0.34
     internazionale
    -0.34
     redacción
    -0.34
    dafx
    -0.34
    POSITIVE LOGITS
     capability
    1.21
     Capability
    1.13
     ability
    1.13
     capacity
    1.09
     Capabilities
    1.09
    capacity
    1.08
     capabilities
    1.05
     Ability
    1.05
     Capacity
    1.04
    capability
    1.04
    Activations Density 0.197%

    No Known Activations