© 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
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 10068
    Prev
    Next
    INDEX
    Explanations

    themes related to family structures and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.49
    醐
    -0.39
     tě
    -0.37
    chaun
    -0.36
    ANTLR
    -0.36
    /**
    -0.36
    letor
    -0.36
    AsUp
    -0.35
    깅
    -0.35
     Referential
    -0.35
    POSITIVE LOGITS
     filial
    0.79
     independence
    0.77
     parental
    0.73
     adult
    0.73
    自立
    0.66
     parents
    0.65
    ConstraintMaker
    0.64
    孝
    0.64
    parental
    0.64
     emancipation
    0.64
    Activations Density 0.333%

    No Known Activations