© 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. 15549
    Prev
    Next
    INDEX
    Explanations

    elements related to relationships and social dynamics

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

    words and phrases describing wisdom, advice, and intelligent or experienced perspectives.

    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
     betweenstory
    -0.67
    новништво
    -0.57
    transQ
    -0.52
    kloped
    -0.52
    ことができ
    -0.50
     dAtA
    -0.49
    strophy
    -0.49
    Tembelea
    -0.49
    𝟘
    -0.49
     Италијани
    -0.49
    POSITIVE LOGITS
    InteropServices
    0.43
     stället
    0.41
     WIRE
    0.41
    e
    0.41
    wire
    0.39
     يتيمه
    0.39
     Bite
    0.37
     суток
    0.36
    Wire
    0.36
     Wire
    0.36
    Activations Density 1.063%

    No Known Activations