© 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. 9872
    Prev
    Next
    INDEX
    Explanations

    references to interpersonal connections and social knowledge

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

    phrases expressing the desire or effort to become better acquainted with someone or something.

    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
     kasarigan
    -0.47
    principalColumn
    -0.47
    ፩
    -0.40
    KommentareTeilen
    -0.38
    rrggbb
    -0.36
    期刊论文
    -0.35
     albicans
    -0.35
    ujudkan
    -0.35
     пробу
    -0.35
    */),
    -0.34
    POSITIVE LOGITS
     acquaintance
    1.29
     conhecer
    1.23
     acquainted
    1.20
     conocer
    1.17
     conhe
    1.16
     kennen
    1.15
     mengenal
    1.13
     kenal
    1.11
     acquaint
    1.11
     conocemos
    1.10
    Activations Density 0.185%

    No Known Activations