© 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-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 9704
    Prev
    Next
    INDEX
    Explanations

    terms related to capability and ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orth
    -0.45
    ton
    -0.45
    віду
    -0.45
    titleMargin
    -0.45
    <strong>
    -0.44
    is
    -0.43
    to
    -0.42
    8
    -0.42
    BorderLayout
    -0.42
    dos
    -0.41
    POSITIVE LOGITS
     ability
    1.98
     Ability
    1.95
    Ability
    1.91
     abilities
    1.86
     capability
    1.80
    abilities
    1.80
     Capability
    1.79
     capabilities
    1.73
     Abilities
    1.70
     Capabilities
    1.69
    Activations Density 0.053%

    No Known Activations