© 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. 31-GEMMASCOPE-RES-16K
    11. 13101
    Prev
    Next
    INDEX
    Explanations

    terms related to capabilities and standards in protocols and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the verb "are" in contexts where it's used to make categorical or descriptive statements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itself
    -1.23
     its
    -1.23
    Its
    -1.02
     Its
    -1.01
    itself
    -0.96
     оно
    -0.95
    它的
    -0.94
     Оно
    -0.94
    它
    -0.91
     яке
    -0.87
    POSITIVE LOGITS
     themselves
    1.48
    themselves
    1.43
     которые
    1.19
     których
    1.14
     които
    1.11
     amelyek
    1.09
     themſelves
    1.03
     denen
    1.02
     ones
    0.95
     olduk
    0.94
    Activations Density 2.296%

    No Known Activations