© 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. 8070
    Prev
    Next
    INDEX
    Explanations

    concepts related to support and collaboration in relationships

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

    words and phrases describing people working or doing activities together.

    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
    msgTypes
    -0.37
    ﹠
    -0.36
    exitRule
    -0.34
    føring
    -0.33
     myndig
    -0.33
     algemene
    -0.32
    fiehlt
    -0.32
    سری
    -0.32
    forhold
    -0.31
     dår
    -0.31
    POSITIVE LOGITS
     together
    3.31
    together
    3.02
    Together
    3.00
     Together
    2.91
     TOGETHER
    2.78
     juntos
    2.77
     jointly
    2.42
     gemeinsam
    2.30
     collectively
    2.25
     insieme
    2.06
    Activations Density 0.946%

    No Known Activations