© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 90654
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and generational descriptions

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

    younger sibling or child

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Italijani
    -0.51
    脚注の使い方
    -0.50
    المكان
    -0.46
    Kjelder
    -0.44
     مشين
    -0.41
     pulumi
    -0.41
    SOUNDBITE
    -0.41
    indari
    -0.40
    jooq
    -0.39
    出版年
    -0.38
    POSITIVE LOGITS
     brother
    2.52
     sister
    2.38
    brother
    2.20
     cousin
    2.17
     sibling
    2.08
     nephew
    2.03
    sister
    1.99
     brothers
    1.95
     siblings
    1.92
     Brother
    1.91
    Activations Density 0.201%

    No Known Activations