© 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. 25-GEMMASCOPE-RES-16K
    11. 4819
    Prev
    Next
    INDEX
    Explanations

    references to authority and accountability in a relational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    homonymie
    -0.74
    usercontent
    -0.65
     ComVisible
    -0.65
    AndEndTag
    -0.64
    tagHelperRunner
    -0.63
    بوابة
    -0.60
     impar
    -0.59
    SpringBootTest
    -0.58
    はじめに
    -0.58
    monition
    -0.56
    POSITIVE LOGITS
     constantly
    0.94
     continually
    0.90
     continuously
    0.85
     act
    0.79
     refuses
    0.78
     repeatedly
    0.77
     CONSTANT
    0.74
     blatantly
    0.74
     claimed
    0.73
     refused
    0.73
    Activations Density 0.461%

    No Known Activations