© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 14523
    Prev
    Next
    INDEX
    Explanations

    terms related to power and its various forms and implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.86
     doubtnut
    -0.84
     Jams
    -0.77
    toMatchSnapshot
    -0.72
     skippy
    -0.72
     Monks
    -0.71
    GEBURTS
    -0.70
    __:
    -0.68
    Personensuche
    -0.68
    classifiers
    -0.67
    POSITIVE LOGITS
     power
    3.81
     Power
    3.58
    power
    3.48
    Power
    3.44
     POWER
    3.16
    POWER
    3.16
     powers
    2.56
    powers
    2.53
     Powers
    2.44
    Powers
    2.28
    Activations Density 0.064%

    No Known Activations