© 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 - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 13204
    Prev
    Next
    INDEX
    Explanations

    expressions of ability or capability, particularly using the word "can."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.76
     indisponible
    -0.66
     Cord
    -0.54
    互联网档案馆
    -0.53
     betweenstory
    -0.52
    といけない
    -0.52
     Foundation
    -0.50
    rin
    -0.49
    WriteTagHelper
    -0.49
    Foundation
    -0.48
    POSITIVE LOGITS
     attest
    0.89
     assure
    0.79
     testify
    0.78
     vouch
    0.76
    ChildScrollView
    0.75
    Autoritní
    0.75
    testify
    0.70
     guarantee
    0.70
     imagine
    0.70
     honestly
    0.69
    Activations Density 0.113%

    No Known Activations