© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 7781
    Prev
    Next
    INDEX
    Explanations

    terms related to caregiving and loss, particularly focusing on loved ones and family connections

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

    phrases about family members and close relationships, particularly in contexts involving loss, separation, or emotional connection.

    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
    SharedDtor
    -0.43
     فريبيس
    -0.43
     lek
    -0.43
     öss
    -0.39
    "]];
    -0.39
    TryDecodeAsNil
    -0.38
    ArrowToggle
    -0.38
    "]).
    -0.37
     насељу
    -0.37
    enteuer
    -0.36
    POSITIVE LOGITS
     loved
    1.79
    loved
    1.52
     Loved
    1.41
    Loved
    1.37
     LOVED
    1.20
     beloved
    1.08
     gelieb
    0.93
     dear
    0.91
     عزی
    0.88
     loves
    0.85
    Activations Density 0.167%

    No Known Activations